© 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. 25-GEMMASCOPE-RES-16K
    11. 2811
    Prev
    Next
    INDEX
    Explanations

    static keyword usages in programming code, particularly related to class definitions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     static
    -0.72
     Majefty
    -0.54
    static
    -0.53
    ]));
    -0.53
     OMITBAD
    -0.52
     still
    -0.48
    endregion
    -0.47
    EXCEPT
    -0.47
    kuuta
    -0.47
    Protocols
    -0.46
    POSITIVE LOGITS
    ally
    0.98
    enterOuterAlt
    0.77
    ALLY
    0.71
     readonly
    0.65
     constexpr
    0.62
    protoimpl
    0.61
    too
    0.58
     too
    0.57
     EconPapers
    0.56
    zny
    0.56
    Activations Density 0.146%

    No Known Activations