© 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. 70645
    Prev
    Next
    INDEX
    Explanations

    references to email-related security measures and issues

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

    prevent or stop actions

    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
     transfieras
    -0.74
    AndEndTag
    -0.57
    GTCX
    -0.57
    SequentialGroup
    -0.54
    styleType
    -0.54
    PreferredItem
    -0.53
    
    -0.52
     kasarigan
    -0.50
    yntaxException
    -0.49
     resourceCulture
    -0.49
    POSITIVE LOGITS
     fore
    0.40
    TryGetValue
    0.39
     Tan
    0.35
     Mitarbeit
    0.35
     Fore
    0.35
     détect
    0.34
     detected
    0.33
     rewards
    0.33
     messen
    0.33
     Ts
    0.33
    Activations Density 0.051%

    No Known Activations