© 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. 116969
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and regulatory issues concerning user experience and information integrity

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

    potential future outcomes

    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
    ValueStyle
    -0.80
    httphttps
    -0.75
    MessageTagHelper
    -0.66
    Personensuche
    -0.60
    HostException
    -0.59
    WithIOException
    -0.59
     Normdatei
    -0.57
    IsMutable
    -0.56
     cherchés
    -0.54
    новниш
    -0.54
    POSITIVE LOGITS
     safety
    0.40
    __;
    0.34
     sécurité
    0.34
     risk
    0.33
    月号
    0.33
     безопасность
    0.31
     safeguard
    0.30
     convenience
    0.29
     sicurezza
    0.29
    ěž
    0.29
    Activations Density 0.143%

    No Known Activations