© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 95488
    Prev
    Next
    INDEX
    Explanations

    adjectives that imply a negative or problematic quality

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

    words ending in -ious, -ous, -atious

    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
     ainfi
    -0.99
     Majefty
    -0.91
     miniaturka
    -0.85
     feroit
    -0.84
     Houſe
    -0.79
     auroit
    -0.76
     Inscrivez
    -0.74
     pouvoit
    -0.73
     pleaſure
    -0.73
     purpoſe
    -0.72
    POSITIVE LOGITS
    urous
    0.86
    rous
    0.84
    ous
    0.83
    IOUS
    0.83
    culous
    0.82
    ious
    0.81
    acious
    0.81
    tious
    0.77
    UOUS
    0.77
    titious
    0.76
    Activations Density 0.046%

    No Known Activations