© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10687
    Prev
    Next
    INDEX
    Explanations

    actions related to obtaining or organizing objects and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     vinto
    -0.36
     Vaux
    -0.35
    mjs
    -0.32
    뀔
    -0.31
    onchange
    -0.30
    ául
    -0.30
    ateness
    -0.30
     sans
    -0.30
     cho
    -0.30
     possibility
    -0.29
    POSITIVE LOGITS
     للاسماء
    1.02
    IntoConstraints
    0.82
    OGND
    0.76
    ChildScrollView
    0.72
     surla
    0.69
    TypedDataSet
    0.69
    majánló
    0.68
     Paglinawan
    0.65
    TagMode
    0.64
     дописавши
    0.63
    Activations Density 0.111%

    No Known Activations