© 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. 14522
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to consequences and impact on people and safety in various contexts

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

    harm to others

    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
     AssemblyTitle
    -0.39
    localctx
    -0.36
     Smart
    -0.35
    SerializedName
    -0.35
    ExtendWith
    -0.34
     AppCompatTheme
    -0.34
     smart
    -0.33
    unsqueeze
    -0.33
    이터
    -0.33
    AVIS
    -0.33
    POSITIVE LOGITS
    MethodManager
    0.55
     protoimpl
    0.54
     recevez
    0.50
     للاسماء
    0.50
     invokingState
    0.50
    AndEndTag
    0.49
    ༚
    0.47
     Infórmanos
    0.47
     poème
    0.47
     consommate
    0.46
    Activations Density 0.043%

    No Known Activations