Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1151
    Prev
    Next
    INDEX
    Explanations

    references to the First Amendment and related legal concepts

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

    references to the term "First" related to amendments or initial points in a discussion

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

    introduction or ordinal first

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    %)$
    -0.90
    protoimpl
    -0.88
    rrggbb
    -0.86
    "}"
    -0.85
    })()
    -0.83
    ItemBackground
    -0.82
    enumii
    -0.76
    ")));
    
    -0.76
    .)}
    -0.74
     "}";
    -0.73
    POSITIVE LOGITS
     ever
    0.85
    s
    0.75
     few
    0.74
     thing
    0.66
     responders
    0.66
    fruits
    0.65
    born
    0.64
     tiên
    0.64
     aider
    0.64
     impressions
    0.63
    Activations Density 0.110%

    No Known Activations