Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 5207
    Prev
    Next
    INDEX
    Explanations

    references to tags within a coding or data context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']));
    -0.82
    isNullOrEmpty
    -0.78
    )");
    
    -0.76
    \"");
    -0.74
     Illustrations
    -0.74
    />";
    -0.73
     }}$}
    -0.72
    "]));
    -0.72
    ]]);
    -0.71
    ...");
    
    -0.71
    POSITIVE LOGITS
     tag
    2.58
     Tag
    2.50
     tags
    2.47
    Tag
    2.39
     Tags
    2.28
    tags
    2.21
    tag
    2.14
     TAG
    2.07
    Tags
    2.03
     tagging
    1.92
    Activations Density 0.023%

    No Known Activations