© 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. 5996
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in various contexts, such as legal, consumer, or user interactions

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

    Tokens preceding roles or actors

    np_acts-logits-general · gemini-2.0-flash

    parties or roles in legal or business contexts

    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
     ویکی‌پدی
    -0.86
    InjectAttribute
    -0.82
     Roskov
    -0.74
     ExecuteAsync
    -0.70
     ostavi
    -0.69
    ViewImports
    -0.66
    OGND
    -0.65
    IndentedString
    -0.64
    CppCodeGen
    -0.63
    TypedDataSet
    -0.63
    POSITIVE LOGITS
    iség
    0.61
    們
    0.57
    selves
    0.55
    '
    0.55
     számára
    0.53
    zelf
    0.53
    ’
    0.53
    们
    0.52
     picioare
    0.51
    śmy
    0.51
    Activations Density 0.695%

    No Known Activations