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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8304
    Prev
    Next
    INDEX
    Explanations

    patterns related to data organization or structuring

    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
    <eos>
    -0.63
     ↑
    -0.61
    ourt
    -0.60
    omy
    -0.58
    ceaux
    -0.57
     Curran
    -0.56
     
    -0.55
     entre
    -0.54
    νι
    -0.53
     #
    -0.53
    POSITIVE LOGITS
     للاسماء
    1.22
     незавершена
    1.13
    存于互联网档案馆
    1.12
     initComponents
    0.98
     BoxFit
    0.95
     resourceCulture
    0.93
     defaultstate
    0.90
    లాలు
    0.90
    </caption>
    0.88
     StatelessWidget
    0.87
    Activations Density 0.015%

    No Known Activations