© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 778
    Prev
    Next
    INDEX
    Explanations

    keywords indicating method visibility and access modifiers in programming code

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

    Code declarations (public, static, private)

    np_acts-logits-general · gemini-2.0-flash

    public static

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.62
    regarding
    -0.57
    }^{-}\
    -0.57
    WriteBarrier
    -0.54
    entang
    -0.53
    zent
    -0.53
    abstractmethod
    -0.51
    Bibliografia
    -0.50
     ExecuteAsync
    -0.49
    gart
    -0.49
    POSITIVE LOGITS
     static
    2.40
    static
    2.19
    Static
    1.35
    静态
    1.34
     STATIC
    1.30
     Static
    1.28
    STATIC
    1.19
    staticmethod
    1.04
     静
    1.04
    statics
    0.89
    Activations Density 0.080%

    No Known Activations