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. 12-GEMMASCOPE-RES-16K
    6. 891
    Prev
    Next
    INDEX
    Explanations

    legal and contractual terminology related to obligations and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exacts
    -0.73
     pinulongan
    -0.69
    RectangleBorder
    -0.69
     $_"
    -0.68
    TintMode
    -0.66
     parseFrom
    -0.65
     MainAxisSize
    -0.64
    }(),
    -0.62
    fiez
    -0.61
     }?>
    -0.61
    POSITIVE LOGITS
     فريبيس
    0.48
    RenderAtEndOf
    0.46
     [
    0.44
    wendig
    0.42
    BagLayout
    0.41
    andes
    0.41
     bằng
    0.40
    [:
    0.40
    ρίς
    0.40
     <=",
    0.39
    Activations Density 0.972%

    No Known Activations