© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    elements related to integrity and security in code, particularly those associated with cryptographic hashes

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

    Code, licenses, or file paths

    np_acts-logits-general · gemini-2.0-flash

    user user

    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
     &___
    -0.44
    Сыртқы
    -0.42
    Чыганаклар
    -0.38
    expandindo
    -0.37
     kaynağından
    -0.35
    Rujuakan
    -0.35
     Waray
    -0.34
     wzglę
    -0.34
    zzleHttp
    -0.34
     саны
    -0.32
    POSITIVE LOGITS
    MigrationBuilder
    0.94
     typelib
    0.72
    ceğine
    0.66
    ConstraintMaker
    0.63
     autorytatywna
    0.60
     CWE
    0.59
     surla
    0.57
     defaultstate
    0.56
    DoubleQuotes
    0.55
    principalTable
    0.54
    Activations Density 0.126%

    No Known Activations