© 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. 21310
    Prev
    Next
    INDEX
    Explanations

    the presence of proper nouns and their variations, especially personal or organizational names

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

    initials followed by punctuation

    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
    Ārējās
    -0.37
     []:
    -0.36
     Wirklichkeit
    -0.36
     nasled
    -0.34
     manguera
    -0.33
     versioni
    -0.33
     primeiras
    -0.31
     Fakten
    -0.31
    Enllaços
    -0.31
     kenyataan
    -0.31
    POSITIVE LOGITS
    ########.
    0.81
    AsUp
    0.71
    ItemBackground
    0.68
    makeConstraints
    0.66
    iſen
    0.63
    zaSy
    0.59
    desertcart
    0.58
    ViewImports
    0.58
    aarrggbb
    0.58
    enablog
    0.58
    Activations Density 0.049%

    No Known Activations