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. 58437
    Prev
    Next
    INDEX
    Explanations

    personal experiences and expressions of feelings

    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
    UnusedPrivate
    -0.73
     chi̍t
    -0.67
    intahan
    -0.63
     Granville
    -0.61
    CompleteListener
    -0.61
    NameInMap
    -0.61
     []),
    -0.59
    CopyWith
    -0.58
    omat
    -0.57
     Gass
    -0.56
    POSITIVE LOGITS
     why
    0.96
    why
    0.82
    REASONS
    0.80
     Whyte
    0.80
     reasons
    0.79
    Почему
    0.75
    为什么
    0.73
     varför
    0.71
     WHY
    0.70
    Why
    0.69
    Activations Density 0.024%

    No Known Activations