© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 104
    Prev
    Next
    INDEX
    Explanations

    phrases that express requests for feedback or interaction from the audience

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

    Requests for opinions or feedback

    np_acts-logits-general · gemini-2.0-flash

    asking for thoughts and feedback

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    /**
    -0.61
    MigrationBuilder
    -0.60
     fufficient
    -0.57
    resave
    -0.49
     Sufficient
    -0.48
    omock
    -0.48
     ComVisible
    -0.48
    pography
    -0.47
    はじめに
    -0.47
    といけない
    -0.46
    POSITIVE LOGITS
     feedback
    1.20
     suggestions
    1.17
     comments
    1.09
     comment
    0.96
     Comments
    0.96
     Suggestions
    0.94
     Feedback
    0.93
    comments
    0.92
     submissions
    0.91
     share
    0.91
    Activations Density 0.213%

    No Known Activations