© 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. 7874
    Prev
    Next
    INDEX
    Explanations

    references to governmental structures and roles

    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
     surla
    -0.52
    agaan
    -0.45
    niſſe
    -0.45
    comet
    -0.44
    stateMutability
    -0.42
     متعلقه
    -0.41
    ConstraintMaker
    -0.40
     ddelwed
    -0.40
    homonymie
    -0.40
     Interpreter
    -0.40
    POSITIVE LOGITS
     chair
    2.97
     Chair
    2.86
    Chair
    2.73
     chairman
    2.59
     Chairman
    2.56
    chair
    2.55
     CHAIR
    2.50
     chairs
    2.44
    Chairman
    2.41
     chairperson
    2.34
    Activations Density 0.380%

    No Known Activations