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. 9-GEMMASCOPE-RES-16K
    6. 9378
    Prev
    Next
    INDEX
    Explanations

    references to tags and tagging systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isNullOrEmpty
    -0.79
    )];
    
    -0.76
    ']));
    -0.75
     Illustrations
    -0.74
    ...");
    
    -0.73
    />";
    -0.73
    ]));
    
    -0.71
    )");
    
    -0.71
     تانيه
    -0.70
    
    
    -0.70
    POSITIVE LOGITS
     tag
    2.14
     tags
    2.11
     Tag
    2.04
     Tags
    1.96
    Tag
    1.91
    tags
    1.87
     TAG
    1.77
    Tags
    1.76
    tag
    1.71
    WithTag
    1.63
    Activations Density 0.034%

    No Known Activations