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. 43415
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with platforms, forums, and networking in various contexts

    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
     dedo
    -0.50
     côtes
    -0.47
    туга
    -0.45
    числи
    -0.45
     pronon
    -0.44
    mare
    -0.44
     Глу
    -0.44
     profondità
    -0.43
     secondo
    -0.43
    zulegen
    -0.43
    POSITIVE LOGITS
     environment
    0.91
     environments
    0.88
     platform
    0.82
    opportunity
    0.82
     platforms
    0.81
    Opportunities
    0.81
    environments
    0.80
     prostředí
    0.78
     opportunity
    0.77
    opportunities
    0.77
    Activations Density 0.154%

    No Known Activations