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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 1630
    Prev
    Next
    INDEX
    Explanations

    the word "anyway" in various forms as a conversational transition

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

    transitional anyway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.85
     يتيمه
    -0.81
    Билгалдахарш
    -0.77
     صوتيه
    -0.72
    хьтан
    -0.71
    elemField
    -0.68
     AssemblyCulture
    -0.67
    ReusableCell
    -0.66
    ///</
    -0.65
    digarh
    -0.63
    POSITIVE LOGITS
    ay
    0.37
    .*")]
    0.36
    amento
    0.36
    amenti
    0.36
     Hidup
    0.35
    ano
    0.34
     else
    0.33
    able
    0.32
    PENDING
    0.31
     Hoffnung
    0.31
    Activations Density 0.011%

    No Known Activations