© 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. 23383
    Prev
    Next
    INDEX
    Explanations

    words and expressions that convey the idea of foolishness or incompetence

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

    stupid or silly

    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
    __(/*!
    -0.60
    HasAnnotation
    -0.57
    IntoConstraints
    -0.54
    󠁢
    -0.53
     confronti
    -0.52
     PCC
    -0.52
    RTEX
    -0.50
    AnchorStyles
    -0.50
     față
    -0.50
    rungsseite
    -0.50
    POSITIVE LOGITS
    stupid
    1.03
     Stupid
    1.02
    Stupid
    1.02
     stupid
    1.00
     silly
    0.84
    dumb
    0.76
    Silly
    0.75
     Silly
    0.73
     foolish
    0.71
     stupidly
    0.71
    Activations Density 0.007%

    No Known Activations