© 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. 9597
    Prev
    Next
    INDEX
    Explanations

    references to components and modules in the context of programming or software development

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

    React components, reducers, or code imports

    np_acts-logits-general · gemini-2.0-flash

    programming constructs and imports

    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
    $_['
    -0.58
    ?(
    -0.58
    ++;
    -0.51
    oplasma
    -0.49
    :\
    -0.48
    ?).
    -0.46
    ((
    -0.46
    --;
    -0.45
     HOLL
    -0.45
    줘
    -0.45
    POSITIVE LOGITS
    Tikang
    0.79
    tagHelperRunner
    0.76
    DockStyle
    0.75
    DoubleQuotes
    0.73
     AssemblyCulture
    0.69
     通販
    0.64
    aarrggbb
    0.64
     CreateTagHelper
    0.62
     мәкал
    0.61
     }
    0.61
    Activations Density 0.037%

    No Known Activations