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. 15735
    Prev
    Next
    INDEX
    Explanations

    phrases that describe perceptions and qualities of objects or experiences

    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
    });*/
    -0.75
    )");
    
    -0.70
    }));
    
    -0.70
     CanadaChoose
    -0.66
    "){
    -0.66
    ++){
    
    -0.66
    )";
    
    -0.66
    ")){
    
    -0.65
    )*/
    -0.65
    ("")]
    
    -0.65
    POSITIVE LOGITS
    looks
    1.12
    Looks
    1.09
     Looks
    1.09
     looks
    1.08
     appear
    0.96
     APPE
    0.94
     sounded
    0.93
     appears
    0.93
     sounding
    0.90
     looked
    0.88
    Activations Density 0.174%

    No Known Activations