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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2338
    Prev
    Next
    INDEX
    Explanations

    references to specific authors or editors in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Cañete, Tourette, Play Store

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vnto
    -0.56
     Pardon
    -0.45
     scratching
    -0.44
    HasForeignKey
    -0.42
     himſelf
    -0.41
     Entomol
    -0.41
     pageNo
    -0.41
     Klon
    -0.41
     labial
    -0.40
    Chham
    -0.40
    POSITIVE LOGITS
     الحره
    0.71
     intptr
    0.69
     wireType
    0.69
    yntaxException
    0.68
    AutoScaleMode
    0.65
    ChildIndex
    0.64
    GeneratedCode
    0.63
     ExecuteAsync
    0.63
    seamnă
    0.62
     ReactDOM
    0.62
    Activations Density 0.099%

    No Known Activations