© 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. 36-GEMMASCOPE-RES-16K
    11. 8335
    Prev
    Next
    INDEX
    Explanations

    phrases indicating advice or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parseFrom
    -0.43
    Portály
    -0.41
    enterOuterAlt
    -0.40
    optionalTypeArgs
    -0.35
     combineReducers
    -0.35
    最多的
    -0.34
    OuterAlt
    -0.33
    principalColumn
    -0.33
    WebServlet
    -0.33
     ErrInvalid
    -0.33
    POSITIVE LOGITS
     better
    3.83
    better
    3.59
    Better
    3.42
     Better
    3.30
     BETTER
    2.92
     mejor
    2.78
     besser
    2.61
     meglio
    2.53
     melhor
    2.52
     mieux
    2.48
    Activations Density 0.588%

    No Known Activations