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 - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8200
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations or names associated with the Bay Area

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.69
     Hopf
    -0.56
     cảm
    -0.55
     nadie
    -0.52
    ControllerAdvice
    -0.51
    createObject
    -0.51
     Chasse
    -0.50
    IContainer
    -0.50
    TextWatcher
    -0.49
     affid
    -0.48
    POSITIVE LOGITS
     Bay
    0.82
    Bay
    0.79
     bay
    0.78
    seventh
    0.75
     sunny
    0.75
    Fifth
    0.75
    fifth
    0.73
     Fifth
    0.72
     fifth
    0.72
     Frye
    0.70
    Activations Density 0.112%

    No Known Activations