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. 43467
    Prev
    Next
    INDEX
    Explanations

    references to significant events or phenomena that can have far-reaching impacts, particularly in the context of economics and environmental issues

    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
    Спољашње
    -0.66
     SEDS
    -0.62
    itinéraire
    -0.62
    Legături
    -0.60
    Iden
    -0.60
    
    -0.57
     CURIAM
    -0.57
    Hauptartikel
    -0.56
    modelBuilder
    -0.56
     ujednoznacz
    -0.56
    POSITIVE LOGITS
     viewType
    0.50
     Virus
    0.49
    awtextra
    0.49
     virus
    0.47
     pukul
    0.47
     tør
    0.45
     era
    0.44
    vál
    0.44
    ätta
    0.43
    outState
    0.43
    Activations Density 0.209%

    No Known Activations