© 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. 22-GEMMASCOPE-RES-16K
    11. 7612
    Prev
    Next
    INDEX
    Explanations

    data structure terms commonly used in programming, especially collections and data containers

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

    List of something

    np_acts-logits-general · gemini-2.0-flash

    List `List` and `Set` generics

    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
    addContainerGap
    -0.77
    RunWith
    -0.68
     defStyle
    -0.60
    HasAnnotation
    -0.55
     ?>>
    -0.54
     [];
    -0.54
     !$
    -0.54
     .
    -0.53
     /\.(
    -0.53
     defStyleAttr
    -0.53
    POSITIVE LOGITS
    <
    0.75
    <?
    0.71
    makeConstraints
    0.55
     bpy
    0.53
    Története
    0.52
    testcase
    0.49
    `
    0.49
    Erreferentziak
    0.46
    jning
    0.46
    rabble
    0.44
    Activations Density 0.037%

    No Known Activations