© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 96022
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations, particularly associated with places and entities

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

    geographic locations and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AsyncTask
    -0.38
    RenderAtEndOf
    -0.35
    Spoljašnje
    -0.34
    bership
    -0.33
    omiast
    -0.33
    alyptus
    -0.32
    kään
    -0.32
     Zeug
    -0.31
    oides
    -0.30
     odkazy
    -0.30
    POSITIVE LOGITS
    IntoConstraints
    0.63
    省市镇
    0.59
     County
    0.56
     city
    0.56
     invokingState
    0.55
    ंदीखरीदारी
    0.54
     Province
    0.53
     province
    0.52
     City
    0.51
     ciudad
    0.51
    Activations Density 0.104%

    No Known Activations