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. 58375
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or a lack of something

    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
    PhysRev
    -0.79
    vábbi
    -0.68
     copii
    -0.66
    onsored
    -0.65
     disambiguazione
    -0.63
     frumos
    -0.63
     aastal
    -0.59
     employe
    -0.58
     kwanza
    -0.58
     whereof
    -0.57
    POSITIVE LOGITS
    rolid
    0.74
     McQu
    0.73
     certainly
    0.72
    argli
    0.70
     indeed
    0.70
     bukan
    0.68
    abelle
    0.68
    yntax
    0.67
     Bukan
    0.65
    twimg
    0.64
    Activations Density 0.013%

    No Known Activations