© 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. 94901
    Prev
    Next
    INDEX
    Explanations

    prominent nouns and proper nouns within the text

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

    a note, national, difficulty, addition, theoretical

    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
    JAKARTA
    -0.39
    Witam
    -0.39
    Népesség
    -0.37
     AssemblyCulture
    -0.35
    delwed
    -0.33
    quiao
    -0.32
    ruik
    -0.32
    lexikon
    -0.32
     identity
    -0.32
     skilled
    -0.32
    POSITIVE LOGITS
     betreft
    0.59
     kasarigan
    0.56
    exitRule
    0.55
    ValueStyle
    0.53
     wiedzieć
    0.52
    GOTREF
    0.52
    دانشنامهٔ
    0.50
    principalTable
    0.50
    setVerticalGroup
    0.48
     przyp
    0.47
    Activations Density 0.013%

    No Known Activations