© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4292
    Prev
    Next
    INDEX
    Explanations

    programming structures and operations, particularly related to functions, variables, and database inserts

    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
    angnya
    -0.49
    terie
    -0.48
    RTCF
    -0.47
     trimmer
    -0.46
     hidupnya
    -0.46
    IUrlHelper
    -0.46
     Gefähr
    -0.45
     Alter
    -0.44
    verge
    -0.44
     Coupons
    -0.44
    POSITIVE LOGITS
    <bos>
    0.88
    ViewImports
    0.63
    GeneratedValue
    0.59
     MainAxisSize
    0.59
     استنادى
    0.57
    RectangleBorder
    0.57
    تقاوى
    0.56
     doPost
    0.55
     pageContext
    0.54
    multer
    0.54
    Activations Density 0.337%

    No Known Activations