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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2602
    Prev
    Next
    INDEX
    Explanations

    expressions of enthusiasm or positive sentiment, particularly using the word "awesome."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.74
    )_{\
    -0.70
    Stil
    -0.70
    Zal
    -0.70
    Portail
    -0.70
    valget
    -0.69
     Qua
    -0.69
     Gol
    -0.68
     Kem
    -0.67
    yid
    -0.67
    POSITIVE LOGITS
     shirts
    0.96
     shirt
    0.92
     Shirts
    0.92
     Shirt
    0.90
     ejus
    0.87
    Shirts
    0.86
     weiss
    0.84
     Cicero
    0.83
    خدام
    0.82
    shirt
    0.82
    Activations Density 0.081%

    No Known Activations