© 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. 2661
    Prev
    Next
    INDEX
    Explanations

    structures or constructs in programming languages

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

    C/C++ data types

    np_acts-logits-general · gemini-2.0-flash

    C/C++ programming keywords and types

    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
    mybatisplus
    -0.81
     OkHttpClient
    -0.78
     pleaſure
    -0.68
     MotionEvent
    -0.68
    TextWatcher
    -0.68
    prepareStatement
    -0.67
    extAlignment
    -0.67
     cauſe
    -0.66
     SqlCommand
    -0.66
     purpoſe
    -0.65
    POSITIVE LOGITS
    int
    0.91
    static
    0.65
     int
    0.64
    auto
    0.63
    char
    0.63
    double
    0.59
    httphttps
    0.59
    bool
    0.58
    float
    0.57
    long
    0.55
    Activations Density 0.094%

    No Known Activations