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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43427
    Prev
    Next
    INDEX
    Explanations

    terms related to accuracy and efficiency metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Documented
    -0.84
    inghouse
    -0.76
    uent
    -0.75
     hábiles
    -0.73
    quent
    -0.72
     Varela
    -0.72
     Tuf
    -0.71
    Precise
    -0.71
    excellents
    -0.71
    Hô
    -0.71
    POSITIVE LOGITS
     متعلقه
    0.87
    ities
    0.66
     sterility
    0.65
    Биография
    0.63
     incontinence
    0.63
     समीक्षाओं
    0.63
     adresa
    0.63
    inputType
    0.62
    épendance
    0.61
     Privacidade
    0.61
    Activations Density 0.016%

    No Known Activations