© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15871
    Prev
    Next
    INDEX
    Explanations

    technical parameters and data types related to system configurations

    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
    enguin
    -0.65
    LÄ
    -0.62
    ineſs
    -0.60
    )|^{
    -0.59
     -¿
    -0.58
     ſtill
    -0.58
    ifflin
    -0.58
    شكرا
    -0.56
    Debe
    -0.56
     "/";
    -0.55
    POSITIVE LOGITS
    DoubleQuotes
    0.98
    onedDateTime
    0.92
     Picchu
    0.79
    extAlignment
    0.77
    gamesh
    0.76
    ⓘ
    0.75
    ToBounds
    0.74
    multer
    0.73
     الرياضيه
    0.72
    endphp
    0.71
    Activations Density 0.063%

    No Known Activations