Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 9331
    Prev
    Next
    INDEX
    Explanations

    function and variable definitions in programming language code, particularly related to standard libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstanceState
    -0.58
     frets
    -0.58
    %");
    -0.58
     chi̍t
    -0.54
     gaun
    -0.54
    ிரு
    -0.54
    iedades
    -0.52
    ệp
    -0.51
    frag
    -0.50
     acu
    -0.50
    POSITIVE LOGITS
    EndContext
    1.74
    
    1.17
     consultato
    1.11
    setVerticalGroup
    0.97
     الاطلاع
    0.93
    yarnpkg
    0.91
    日閲覧
    0.91
     UIKit
    0.88
    arXiv
    0.84
    ISupport
    0.84
    Activations Density 0.002%

    No Known Activations