© 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. 3-GEMMASCOPE-RES-16K
    6. 12183
    Prev
    Next
    INDEX
    Explanations

    mentions of fans and fan-related concepts or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.75
     transfieras
    -0.69
     gaun
    -0.67
     pinulongan
    -0.67
    )");
    
    -0.67
     متعلقه
    -0.66
     propOrder
    -0.66
     }));
    -0.65
    )";
    
    -0.65
    ))))))))
    -0.65
    POSITIVE LOGITS
     fan
    3.35
    Fan
    3.09
     Fan
    3.04
    fan
    3.02
     fans
    2.98
     Fans
    2.82
     FAN
    2.80
    FAN
    2.71
    fans
    2.67
    Fans
    2.61
    Activations Density 0.044%

    No Known Activations