© 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. 8317
    Prev
    Next
    INDEX
    Explanations

    formatted strings and placeholders typically used in error messages or logging statements

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

    C format specifiers (%d, %s, %@, etc.)

    np_acts-logits-general · gemini-2.0-flash

    format specifiers and punctuation

    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
     كومونز
    -0.69
    __);
    -0.68
    ''')
    -0.66
    '}>
    -0.65
    __))
    -0.65
    ++)
    -0.60
    '>";
    -0.59
     />';
    -0.58
     насељу
    -0.58
    HEAST
    -0.58
    POSITIVE LOGITS
    ”,
    0.79
    !",
    0.78
    ",
    0.78
     AssemblyCulture
    0.75
    ",(
    0.74
    !”,
    0.73
     ”,
    0.71
    ,”
    0.70
    `,
    0.67
    '',
    0.66
    Activations Density 0.093%

    No Known Activations