© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9152
    Prev
    Next
    INDEX
    Explanations

    elements related to updates and summaries from applications or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML heading tags (h1-h5) and table body tags

    np_acts-logits-general · gemini-2.0-flash

    web page section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '],
    
    -0.98
    "],
    
    -0.96
    '];
    
    -0.93
     ';
    
    -0.93
    .";
    
    -0.92
    ']);
    
    -0.91
    >',
    -0.88
    ]."
    -0.88
    >",
    -0.87
    ."),
    -0.87
    POSITIVE LOGITS
    </h2>
    1.29
    </h3>
    1.26
    </h1>
    1.03
    </h5>
    1.01
    </h4>
    0.82
    <tbody>
    0.78
    Permalink
    0.72
    例文帳に追加
    0.71
    ↵↵↵
    0.65
    <h3>
    0.62
    Activations Density 0.120%

    No Known Activations