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. 11-GEMMASCOPE-RES-16K
    6. 1801
    Prev
    Next
    INDEX
    Explanations

    programming languages and their related files or syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----</
    -0.56
    ']/
    -0.47
     labor
    -0.45
     domestic
    -0.44
     modern
    -0.43
     Chwiliwch
    -0.43
     }}^{\
    -0.42
     Par
    -0.42
     of
    -0.42
    perature
    -0.42
    POSITIVE LOGITS
    存于互联网档案馆
    0.82
    Lähteet
    0.80
    ynb
    0.77
     חיצוניים
    0.77
    IntoConstraints
    0.76
    مراجع
    0.76
    xaml
    0.75
     Audiodateien
    0.75
    jsxFileName
    0.74
    qrstuvwxyz
    0.73
    Activations Density 0.140%

    No Known Activations