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. 11740
    Prev
    Next
    INDEX
    Explanations

    function declarations and expressions in code snippets

    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
    ing
    -0.73
    est
    -0.68
    al
    -0.61
    )}_
    -0.60
     few
    -0.59
     maquina
    -0.59
    wsze
    -0.58
     universel
    -0.58
    草
    -0.58
    ING
    -0.56
    POSITIVE LOGITS
    (()
    1.33
    ={()
    1.04
     ()
    0.81
    pidou
    0.80
    rogly
    0.80
     MonoBehaviour
    0.78
    InputTagHelper
    0.76
     оригіналу
    0.76
    pportun
    0.74
    rometry
    0.73
    Activations Density 0.037%

    No Known Activations