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. 11-GEMMASCOPE-RES-16K
    6. 6902
    Prev
    Next
    INDEX
    Explanations

    elements related to actions, specifically movements and systems in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.74
    FormTagHelper
    -0.72
     Paglinawan
    -0.69
    RTLR
    -0.68
    TagMode
    -0.66
    indd
    -0.64
    ✨:
    -0.62
    TintMode
    -0.62
    ]-->
    -0.62
     @"/
    -0.61
    POSITIVE LOGITS
     or
    0.84
     oder
    0.77
     eller
    0.69
     või
    0.68
     atau
    0.68
     vagy
    0.67
     any
    0.66
     или
    0.66
     quelconque
    0.65
    거나
    0.65
    Activations Density 0.879%

    No Known Activations