© 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. 5513
    Prev
    Next
    INDEX
    Explanations

    references to evidence and quotations in legal contexts

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

    Comes before brackets or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    legal conclusion[s]

    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
    "]}
    -0.80
     ?>/
    -0.80
    )");
    -0.78
    "]];
    -0.76
    ")]
    -0.75
    )";
    -0.74
    ")}
    -0.74
    '},
    -0.74
    原始内容存档于
    -0.74
    ']);
    -0.73
    POSITIVE LOGITS
    ‍
    0.60
    ⎈
    0.58
    ↴
    0.47
    シップ
    0.46
    newtheorem
    0.46
    remera
    0.46
    が発
    0.45
    tillon
    0.45
    wikidata
    0.45
     Smiley
    0.45
    Activations Density 0.136%

    No Known Activations