© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8908
    Prev
    Next
    INDEX
    Explanations

    error handling and logging statements in code

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

    Code with unbalanced parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Raw
    -0.52
     empower
    -0.50
    kare
    -0.49
     nawr
    -0.49
    raw
    -0.49
     special
    -0.48
     sain
    -0.48
     fı
    -0.47
     Raw
    -0.47
    dillera
    -0.46
    POSITIVE LOGITS
     ویکی‌پدیای
    0.79
    NOPQRST
    0.78
     المعيارى
    0.75
    MigrationBuilder
    0.70
    webElementXpaths
    0.68
    adaptiveStyles
    0.67
     unknownFields
    0.65
    goto
    0.64
    Slf
    0.62
     nakalista
    0.62
    Activations Density 0.071%

    No Known Activations