© 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. 0-GEMMASCOPE-RES-16K
    6. 2531
    Prev
    Next
    INDEX
    Explanations

    references to different types of 'heads', particularly in medical or contextual uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.68
     ModelExpression
    -0.52
    AutoresizingMask
    -0.49
    RegressionTest
    -0.48
    TypedDataSet
    -0.44
     mukaan
    -0.43
     PeEnEo
    -0.41
    InitVars
    -0.40
    migrationBuilder
    -0.39
    uidado
    -0.39
    POSITIVE LOGITS
     Head
    0.68
     head
    0.65
    head
    0.64
     HEAD
    0.63
     heads
    0.63
    HEAD
    0.63
    heads
    0.61
    Head
    0.61
     Dor
    0.60
    Dor
    0.58
    Activations Density 1.725%

    No Known Activations