© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67152
    Prev
    Next
    INDEX
    Explanations

    sentences that express strong opinions or emotional responses

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

    foreign language words

    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
     queſta
    -0.64
     lcm
    -0.59
    جغرافيا
    -0.59
    findpost
    -0.59
    MethodManager
    -0.59
    TestingModule
    -0.58
    ⤹
    -0.58
    Cyfeiriadau
    -0.57
    batore
    -0.56
    出版年
    -0.56
    POSITIVE LOGITS
     básica
    0.30
    impianto
    0.29
     bapak
    0.29
     morire
    0.29
    pañas
    0.28
     hermanos
    0.28
     stolz
    0.27
     powinna
    0.26
     folosit
    0.26
     dumne
    0.26
    Activations Density 0.038%

    No Known Activations