© 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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15405
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions, mathematical disciplines, and publications related to mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     nahilalakip
    -0.77
     فريبيس
    -0.73
    aarrggbb
    -0.64
     resourceCulture
    -0.61
    évaluateur
    -0.59
    postsleuth
    -0.59
     nakalista
    -0.58
    WriteTagHelper
    -0.57
     ویکی‌پدی
    -0.57
    Hauptartikel
    -0.57
    POSITIVE LOGITS
     mathematics
    0.77
     mathematical
    0.69
     Mathematics
    0.67
     mathematician
    0.66
     mathematicians
    0.65
    Mathematics
    0.65
     MATHEMATICS
    0.63
     matemáticas
    0.61
     Mathematical
    0.60
     maths
    0.60
    Activations Density 0.701%

    No Known Activations