© 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. 4914
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and methodology

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

    academic or scientific paper introductions that describe a new method, approach, or technique being presented by the authors.

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

    novel methodologies and experimental approaches described in scientific papers.

    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
     Traditional
    -0.48
     traditionally
    -0.48
    familiar
    -0.47
    Traditional
    -0.47
     traditional
    -0.47
     familiar
    -0.46
    traditional
    -0.45
     Typical
    -0.44
     Familiar
    -0.44
     traditionnel
    -0.43
    POSITIVE LOGITS
     novel
    0.89
     method
    0.82
     methodology
    0.82
     efficient
    0.77
     framework
    0.74
     scalable
    0.73
    novel
    0.70
     móds
    0.70
     improved
    0.69
    method
    0.68
    Activations Density 1.527%

    No Known Activations