© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6741
    Prev
    Next
    INDEX
    Explanations

    technical terms related to drugs and chemical classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    bureaucratic or research project details, including funding sources, project names, and organizational structures.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    formal organizational or institutional text with emphasis on projects, initiatives, frameworks, and collaborations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    academic and technical document structure including citations, funding acknowledgments, project acronyms, and formal research metadata.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     econômica
    -0.61
    참고
    -0.60
    Tikang
    -0.59
    WireFormatLite
    -0.57
    WebVitals
    -0.54
     CreateTagHelper
    -0.54
    ̈́
    -0.54
     GreatSchools
    -0.49
    tagHelperRunner
    -0.48
     $\$
    -0.46
    POSITIVE LOGITS
     EU
    0.78
     European
    0.72
     envisaged
    0.66
     innovative
    0.62
     specialised
    0.60
    European
    0.60
    european
    0.59
     analysed
    0.58
    innovative
    0.58
     realised
    0.57
    Activations Density 0.806%

    No Known Activations