© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 15755
    Prev
    Next
    INDEX
    Explanations

    C preprocessor directives and comments in code

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

    Preprocessor directives (e.g., #if, #endif, #pragma)

    np_acts-logits-general · gemini-2.0-flash

    C++ directives like #if, #ifndef, #pragma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rujuakan
    -0.55
    {}{}
    -0.53
     prefier
    -0.52
    ukone
    -0.48
     reach
    -0.48
     Audiodateien
    -0.47
    \
    -0.46
    atst
    -0.44
     везе
    -0.44
    BeginInit
    -0.43
    POSITIVE LOGITS
    region
    0.83
    endregion
    0.78
     arşivlendi
    0.78
    AndEndTag
    0.72
    WithIOException
    0.70
     CreateTagHelper
    0.65
    出版年
    0.64
    nullable
    0.64
    twimg
    0.59
     insuffisamment
    0.59
    Activations Density 0.128%

    No Known Activations