© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14069
    Prev
    Next
    INDEX
    Explanations

    specific terminology and notation related to advanced scientific concepts

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

    Two-letter combinations ending in "p"

    np_acts-logits-general · gemini-2.0-flash

    kip, qp, tp, rip, Ep, ep

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    er
    -0.58
    \"");
    -0.52
    /**
    -0.51
    javax
    -0.50
    userdetails
    -0.49
     "";
    -0.48
    >");
    -0.46
    ."));
    -0.46
     "");
    -0.46
     "";
    -0.46
    POSITIVE LOGITS
     lp
    0.71
     Kip
    0.71
    yp
    0.68
    dp
    0.68
     Jep
    0.67
    pp
    0.66
     KAP
    0.66
    Kip
    0.66
     dp
    0.66
     fp
    0.65
    Activations Density 1.300%

    No Known Activations