© 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-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10020
    Prev
    Next
    INDEX
    Explanations

    references to samples and demo content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    QMetaType
    -0.68
    contentLoaded
    -0.66
     sû
    -0.63
    AccessorTable
    -0.59
    resave
    -0.54
     bestem
    -0.53
     nærm
    -0.52
     gouver
    -0.51
     Versicher
    -0.50
     AGU
    -0.50
    POSITIVE LOGITS
     sample
    1.48
    sample
    1.34
     demo
    1.17
     samples
    1.17
     SAMPLE
    1.13
     Sample
    1.12
    Sample
    1.10
    サンプル
    1.09
    SAMPLE
    1.09
     échanti
    1.05
    Activations Density 0.075%

    No Known Activations