Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 67259
    Prev
    Next
    INDEX
    Explanations

    specific names and references to individuals and institutions

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

    German and Danish places

    np_acts-logits-general · gemini-2.5-flash-lite

    common function words and connecting punctuation, especially articles, short pronouns/prepositions, and possessive or hyphenated forms.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     and
    -0.46
    เย
    -0.37
     tribes
    -0.35
     тран
    -0.35
     نوشت
    -0.35
     its
    -0.34
     &
    -0.34
    intéress
    -0.34
    ViewGroup
    -0.34
     trans
    -0.34
    POSITIVE LOGITS
     betweenstory
    0.95
     '\\;'
    0.77
    RegressionTest
    0.74
    TintMode
    0.71
     Италијани
    0.71
    tanleria
    0.70
     podjela
    0.68
    ⟭
    0.68
    transQ
    0.68
    EDEFAULT
    0.67
    Activations Density 0.049%

    No Known Activations