© 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. 561
    Prev
    Next
    INDEX
    Explanations

    instances of the word "abuse" along with its associated phrases

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

    abuse of, abuse and

    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
    windowFixed
    -0.47
    yarnpkg
    -0.46
    RTN
    -0.46
     dreapta
    -0.43
     Kompon
    -0.43
     للمعارف
    -0.42
     somethin
    -0.42
    wendigkeit
    -0.42
     urč
    -0.42
     Económica
    -0.41
    POSITIVE LOGITS
    Abuse
    1.18
     abuse
    1.17
     Abuse
    1.15
    abuse
    1.04
     abuses
    0.91
     abuso
    0.91
     abusing
    0.89
     abusive
    0.88
     abused
    0.87
     abusers
    0.80
    Activations Density 0.008%

    No Known Activations