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. 6684
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and tags

    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
    DOCTYPE
    -0.66
    Redacción
    -0.63
    .";
    
    -0.62
     vice
    -0.61
     co
    -0.61
    $",
    -0.61
     '',
    
    -0.60
    */
    
    
    -0.60
    KommentareTeilen
    -0.58
    <?
    
    -0.58
    POSITIVE LOGITS
    ">
    0.82
    }>
    0.79
    ↵
    0.78
     }}>
    0.76
    "}}>
    0.72
    }}>
    0.71
    )}>
    0.68
    ="#">
    0.67
    <h3>
    0.67
    '}}>
    0.66
    Activations Density 0.054%

    No Known Activations