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

    Neuronpedia

    APICircuit 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. 12611
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions

    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
    ühm
    -0.59
    ⓧ
    -0.54
    zola
    -0.52
    fördert
    -0.50
    mographie
    -0.49
     Henrietta
    -0.49
    __'
    -0.49
     Corintios
    -0.49
     كورة
    -0.48
     wzor
    -0.48
    POSITIVE LOGITS
    клопе
    0.77
    posedge
    0.73
     Normdatei
    0.62
    WebVitals
    0.60
    archiviato
    0.59
    رشف
    0.58
    jfree
    0.56
    AndEndTag
    0.55
     <=",
    0.52
     newBuilder
    0.52
    Activations Density 0.149%

    No Known Activations