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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8356
    Prev
    Next
    INDEX
    Explanations

    references to items related to stationery and office supplies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.59
     betweenstory
    -0.56
    SequentialGroup
    -0.56
    TokenNameLBRACE
    -0.56
     MainAxisSize
    -0.56
    protoimpl
    -0.54
     comprendre
    -0.54
    MigrationBuilder
    -0.52
     ujednoznacz
    -0.52
    BagConstraints
    -0.51
    POSITIVE LOGITS
     Bonus
    0.83
    Bonus
    0.81
     bonus
    0.80
    bonus
    0.78
     try
    0.69
    Try
    0.69
    Alternatively
    0.68
     Try
    0.68
     Alternatively
    0.67
     alternatively
    0.65
    Activations Density 0.308%

    No Known Activations