© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 8849
    Prev
    Next
    INDEX
    Explanations

    numerical data points and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.88
    featureID
    -0.83
    setVerticalGroup
    -0.80
    writeFieldEnd
    -0.78
     ExecuteAsync
    -0.78
     AssemblyVersion
    -0.77
    HasAnnotation
    -0.76
     Vikipedi
    -0.74
    GIH
    -0.73
    OGND
    -0.72
    POSITIVE LOGITS
    _
    0.64
    MathML
    0.55
     lightness
    0.44
     sani
    0.44
     snaps
    0.43
     Delano
    0.42
     speciation
    0.42
     epa
    0.42
    RequestBuilder
    0.41
     suns
    0.41
    Activations Density 0.163%

    No Known Activations