© 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. 18-GEMMASCOPE-RES-16K
    11. 8942
    Prev
    Next
    INDEX
    Explanations

    abrupt or significant breaks in the text structure or formatting

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    code structure and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ComVisible
    -0.50
    ának
    -0.49
    maco
    -0.49
    努
    -0.49
     start
    -0.47
    BeginContext
    -0.47
    rrggbb
    -0.47
     rồi
    -0.46
     or
    -0.46
    中略
    -0.46
    POSITIVE LOGITS
    expandindo
    1.24
     виправивши
    0.94
    CppMethod
    0.80
    endmodule
    0.75
     iconLine
    0.73
    OGND
    0.72
    fjspx
    0.71
    MigrationBuilder
    0.70
     Chwiliwch
    0.67
    AccessorTable
    0.67
    Activations Density 0.050%

    No Known Activations