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. 554
    Prev
    Next
    INDEX
    Explanations

    patterns related to model loading and processing within a programming context

    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
    >");
    
    -0.64
    </h5>
    -0.62
    )");
    
    -0.62
    "");
    -0.61
    ]";
    -0.61
    )');
    -0.61
    DoubleQuotes
    -0.60
    )";
    
    -0.60
    ]");
    -0.59
    }';
    -0.59
    POSITIVE LOGITS
    ".
    1.30
     ".
    1.26
    '.
    1.21
     '.
    1.08
    .".
    1.03
    !".
    1.03
    ”.
    0.94
    """.
    0.93
    =".
    0.90
    ?".
    0.90
    Activations Density 0.136%

    No Known Activations