© 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. 10562
    Prev
    Next
    INDEX
    Explanations

    keywords related to essential elements or characteristics of subjects

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

    after "signal", "vital", or "dual"

    np_acts-logits-general · gemini-2.0-flash

    vital signal Animal partial

    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
    BeginContext
    -0.62
     Inscrivez
    -0.60
    postIndex
    -0.54
    𝕘
    -0.53
    <tr>
    -0.52
    tilhe
    -0.52
     impresora
    -0.50
    𝕔
    -0.50
    masta
    -0.49
    Yee
    -0.49
    POSITIVE LOGITS
    al
    0.74
    ital
    0.63
    idal
    0.61
    tal
    0.59
    atal
    0.58
    Vital
    0.58
    ñal
    0.57
     Bial
    0.57
    Tal
    0.57
    RAL
    0.57
    Activations Density 0.515%

    No Known Activations