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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 545
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their related formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.73
     بيها
    -0.66
    enumi
    -0.66
    greenrobot
    -0.66
    UrlResolution
    -0.65
    ductors
    -0.61
     (\%
    -0.61
    keyDown
    -0.59
    нциклопе
    -0.59
    adona
    -0.58
    POSITIVE LOGITS
    "");
    0.84
    ");
    0.78
    ),
    0.77
    />";
    0.76
    참고
    0.75
    })).
    0.75
    )).
    0.74
    ).
    0.73
    ),),
    0.73
    ]).
    0.72
    Activations Density 0.786%

    No Known Activations