© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 637
    Prev
    Next
    INDEX
    Explanations

    statements related to expert opinions and consensus on important topics

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

    emphatic affirmations and beliefs regarding dental artistry and care

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

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    tagHelperRunner
    -0.76
    tvguidetime
    -0.69
     MainAxisSize
    -0.57
    Erreferentziak
    -0.55
    rativa
    -0.55
    styleType
    -0.55
    instead
    -0.54
     suggestion
    -0.53
    contentLoaded
    -0.52
    の可能性
    -0.52
    POSITIVE LOGITS
     ensuring
    1.00
     understanding
    0.99
     proper
    0.91
     having
    0.87
     properly
    0.87
    Proper
    0.85
     maintaining
    0.84
     Ensuring
    0.83
     knowing
    0.83
    having
    0.81
    Activations Density 0.148%

    No Known Activations