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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11847
    Prev
    Next
    INDEX
    Explanations

    the word "and" 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 @ 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
    iettes
    -0.60
    Obrázky
    -0.53
    jura
    -0.52
    DataSnapshot
    -0.52
    WEBPACK
    -0.49
     iste
    -0.49
    Geografi
    -0.49
    例文帳に追加
    -0.48
    戚
    -0.48
    kezi
    -0.47
    POSITIVE LOGITS
    Cordialement
    0.78
     '\\;'
    0.71
     يتيمه
    0.69
    发表于
    0.69
    TagHelper
    0.68
     المعيارى
    0.66
    pozdrawiam
    0.66
     Dlatego
    0.65
    expandindo
    0.65
    ؤلاء
    0.64
    Activations Density 0.230%

    No Known Activations