© 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. 13799
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax elements, particularly control flow structures like conditional statements and function declarations

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

    Code switch statements

    np_acts-logits-general · gemini-2.0-flash

    switch case statements

    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
    tagHelperRunner
    -0.70
    новниш
    -0.65
    ofire
    -0.62
    WriteBarrier
    -0.60
    invokeLater
    -0.59
    )];
    -0.59
    клопе
    -0.59
    ,"%
    -0.57
    .")]
    -0.57
    RenderAtEndOf
    -0.57
    POSITIVE LOGITS
     case
    1.45
    case
    1.32
     cases
    1.24
    Case
    1.17
     Case
    1.16
     Cases
    1.16
    Cases
    1.06
     caso
    1.02
    default
    1.02
    cases
    0.99
    Activations Density 0.039%

    No Known Activations