Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 795
    Prev
    Next
    INDEX
    Explanations

    loop control structures in code

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

    "for" loops with index "i" or "j"

    np_acts-logits-general · gemini-2.0-flash

    for loops

    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
     TES
    -0.46
    TES
    -0.42
    CAS
    -0.42
     SAC
    -0.39
    ESL
    -0.39
    Cast
    -0.38
    PAG
    -0.38
     CAS
    -0.38
     которое
    -0.38
     GES
    -0.38
    POSITIVE LOGITS
    DockStyle
    0.58
     Menschheit
    0.58
     desmotivaciones
    0.57
    principalColumn
    0.57
     Bundesrepublik
    0.56
     TÉCN
    0.55
     telefónica
    0.55
    enumi
    0.55
     getItemCount
    0.54
     totalidad
    0.54
    Activations Density 0.068%

    No Known Activations