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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 8713
    Prev
    Next
    INDEX
    Explanations

    comparative language and discussions of relative performance or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    除了
    -0.41
    //
    -0.39
     selain
    -0.35
    À
    -0.31
     alte
    -0.31
    Competing
    -0.30
    除
    -0.30
     competing
    -0.30
     related
    -0.29
     nearby
    -0.29
    POSITIVE LOGITS
     others
    3.64
     Others
    3.38
    Others
    3.36
    others
    3.16
     OTHERS
    2.89
    OTHERS
    2.11
     دیگران
    1.95
    别人
    1.59
    別人
    1.55
     אחרים
    1.52
    Activations Density 0.469%

    No Known Activations