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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14285
    Prev
    Next
    INDEX
    Explanations

    references to locations or points of focus within a spatial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IOException
    -0.52
     Pato
    -0.50
    unlikely
    -0.50
     Koop
    -0.49
     IOException
    -0.48
    appren
    -0.46
    sspiel
    -0.46
    Pato
    -0.43
     gdyby
    -0.42
     griech
    -0.42
    POSITIVE LOGITS
     Center
    1.30
     Centre
    1.20
    Center
    1.19
     center
    1.14
    Centre
    1.09
    center
    1.09
     CENTER
    1.05
     centre
    1.03
     CENTRE
    1.01
     Centers
    0.99
    Activations Density 0.124%

    No Known Activations