© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 54448
    Prev
    Next
    INDEX
    Explanations

    words related to specific historical or political contexts

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

    Hashimi, Acti, TRIB, eff, 手に

    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
    <bos>
    -2.52
    ekš
    -0.69
    vény
    -0.64
    JKLM
    -0.61
    yszer
    -0.59
    lső
    -0.57
    pośred
    -0.57
    Ayy
    -0.57
     zahr
    -0.56
    咙
    -0.56
    POSITIVE LOGITS
    zelfde
    0.82
    ième
    0.79
    ه
    0.66
    iyle
    0.65
    ený
    0.61
    یتی
    0.60
    ی
    0.60
    enchymal
    0.58
    هما
    0.57
    sweise
    0.56
    Activations Density 0.750%

    No Known Activations