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. 10-GEMMASCOPE-RES-16K
    6. 13273
    Prev
    Next
    INDEX
    Explanations

    identifiers and references to data fields or elements in a structured format such as code or database schemas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '.';
    -0.59
    ::_('
    -0.58
     Gould
    -0.57
     Master
    -0.55
    Sé
    -0.54
    UTE
    -0.54
     seiner
    -0.53
    ENDA
    -0.52
     Forced
    -0.51
    ]){
    
    -0.51
    POSITIVE LOGITS
    VersionUID
    0.88
    ClientRect
    0.86
     communautaire
    0.78
    WAUKEE
    0.77
    crollView
    0.76
     typelib
    0.76
    berdayakan
    0.76
    Filmografie
    0.72
    الإنجليزية
    0.72
     comunale
    0.71
    Activations Density 0.332%

    No Known Activations