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. 20-GEMMASCOPE-RES-16K
    6. 1971
    Prev
    Next
    INDEX
    Explanations

    references and claims about documents and their organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    }$.\\
    -1.75
    ).\\
    -1.65
    <eos>
    -1.59
    $.\\
    -1.50
    ).}
    -1.37
    );*/
    -1.26
    ).)
    -1.22
    ↵↵
    -1.21
    ).
    
    -1.21
    ).]
    -1.19
    POSITIVE LOGITS
    .
    0.70
     correctes
    0.69
    Getenv
    0.62
    脚注の使い方
    0.61
     незавершена
    0.57
     NSCoder
    0.54
    CompleteListener
    0.54
    اریخ
    0.53
    Poloha
    0.53
    ؛
    0.51
    Activations Density 1.657%

    No Known Activations