© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10082
    Prev
    Next
    INDEX
    Explanations

    import statements and references to Google libraries in a Java code context

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

    Characters following a period or slash

    np_acts-logits-general · gemini-2.0-flash

    protobuf and android code

    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
    ➟
    -0.87
     invokingState
    -0.86
    webElementXpaths
    -0.74
    jspx
    -0.72
    +:+
    -0.70
    出版年
    -0.68
    WebVitals
    -0.68
     Roskov
    -0.68
    MigrationBuilder
    -0.67
    ItemBackground
    -0.66
    POSITIVE LOGITS
     sona
    0.50
    protobuf
    0.47
    ორ
    0.44
    gson
    0.42
     loto
    0.42
    APOLIS
    0.41
    android
    0.41
    antidad
    0.41
    zx
    0.41
    code
    0.40
    Activations Density 0.125%

    No Known Activations