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. 43338
    Prev
    Next
    INDEX
    Explanations

    references to excessive amounts or levels 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
    r
    -0.81
    l
    -0.79
    ri
    -0.74
    ur
    -0.70
    up
    -0.69
    Portail
    -0.66
    n
    -0.66
    in
    -0.65
    <eos>
    -0.63
     Sit
    -0.63
    POSITIVE LOGITS
     myſelf
    1.51
     Efq
    1.28
     itſelf
    1.25
     poffible
    1.23
     ſeveral
    1.23
     ſever
    1.23
     Monfieur
    1.22
     Theſe
    1.21
     Excessive
    1.19
    wiſe
    1.16
    Activations Density 0.020%

    No Known Activations