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. 4822
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measures of time or quantity

    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
     سكانية
    -0.85
     kasarigan
    -0.80
     protoimpl
    -0.79
     समीक्षक
    -0.73
     صوتيه
    -0.72
    twimg
    -0.70
    }))
    
    -0.69
    +#+
    -0.69
    ttino
    -0.68
    CloseOperation
    -0.67
    POSITIVE LOGITS
     Schmid
    0.48
    setCharacter
    0.48
     Ru
    0.47
    setBold
    0.47
     öğren
    0.47
    iedenen
    0.46
     getSystem
    0.46
     dirigentes
    0.45
    دواج
    0.45
    Ru
    0.45
    Activations Density 0.187%

    No Known Activations