© 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. 20-GEMMASCOPE-RES-16K
    11. 5379
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax related to class definitions and declarations

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

    Keywords related to interfaces and abstract classes

    np_acts-logits-general · gemini-2.0-flash

    problem of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privately
    -0.52
    Coucou
    -0.49
    InBackground
    -0.48
     ElementRef
    -0.46
    Vedi
    -0.45
    bant
    -0.45
     发表于
    -0.45
    uette
    -0.45
     Private
    -0.44
    RTLI
    -0.44
    POSITIVE LOGITS
     void
    0.85
    void
    0.82
     abstract
    0.68
    virtual
    0.66
    abstractmethod
    0.63
    ;"></
    0.63
     virtual
    0.60
    XMLSchema
    0.60
    )}</
    0.60
    AsUp
    0.59
    Activations Density 0.091%

    No Known Activations