© 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. 6259
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to experimental designs and sampling methods in research

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

    technical specifications and quantitative parameters of systems or designs.

    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
    tagHelperRunner
    -0.41
     Feminine
    -0.33
    Multi
    -0.30
     middle
    -0.29
     Bamb
    -0.29
    Femin
    -0.29
    multi
    -0.28
    ientôt
    -0.28
    ustimmung
    -0.27
    Bro
    -0.27
    POSITIVE LOGITS
     arrangements
    1.05
     options
    1.02
     choices
    1.00
     types
    0.94
     arrangement
    0.93
     characteristics
    0.92
     configuration
    0.91
     requirements
    0.91
     strategies
    0.90
     configurations
    0.90
    Activations Density 1.134%

    No Known Activations