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. 9-GEMMASCOPE-RES-131K
    6. 103296
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to foolishness or folly

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

    foolish and unwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.52
     isNameExpr
    -0.40
     tambour
    -0.40
    InputBorder
    -0.40
    fortawesome
    -0.39
     perfección
    -0.38
     spørsmål
    -0.38
     pleaſure
    -0.38
     spørgsmål
    -0.38
     houſe
    -0.37
    POSITIVE LOGITS
     bullish
    1.49
     bearish
    1.29
    olish
    0.89
    kish
    0.83
    ggish
    0.82
     sluggish
    0.73
    endish
    0.69
    mistic
    0.68
     foolish
    0.66
    lish
    0.65
    Activations Density 0.003%

    No Known Activations