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. 11-GEMMASCOPE-RES-16K
    6. 5765
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols used in scientific notation and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trin
    -0.78
     Fé
    -0.75
     Ade
    -0.73
     Gund
    -0.70
     GTR
    -0.70
    ResponseCode
    -0.68
     West
    -0.68
    "+
    
    -0.67
    บัติ
    -0.67
    Gor
    -0.67
    POSITIVE LOGITS
    }]
    1.11
    _]
    1.10
    .]
    1.04
    ″]
    0.94
    \"]
    0.93
    ]]
    0.93
    rfloor
    0.92
     ]
    0.92
    !]
    0.86
    rceil
    0.85
    Activations Density 0.633%

    No Known Activations