© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11085
    Prev
    Next
    INDEX
    Explanations

    occurrences of return statements in programming code

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

    Code or markup delimiters

    np_acts-logits-general · gemini-2.0-flash

    code comments and structures

    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
    parsedMessage
    -1.09
     Biôgrafia
    -0.94
    ðsíða
    -0.90
    ロウィン
    -0.85
     Italijani
    -0.84
    AndEndTag
    -0.84
    featureID
    -0.84
    enablog
    -0.82
     Roskov
    -0.82
    ésultats
    -0.81
    POSITIVE LOGITS
    hline
    0.61
    no
    0.46
    0
    0.45
    section
    0.44
    \[
    0.44
    ↵
    0.42
    with
    0.41
    X
    0.41
    On
    0.41
    With
    0.41
    Activations Density 0.024%

    No Known Activations