© 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. 10972
    Prev
    Next
    INDEX
    Explanations

    words related to various scientific and medical terms

    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
    m
    -0.82
    ness
    -0.74
    s
    -0.71
    baix
    -0.68
    ling
    -0.67
     silêncio
    -0.66
    us
    -0.65
    r
    -0.64
    ms
    -0.64
    masing
    -0.63
    POSITIVE LOGITS
    auso
    1.03
    eo
    0.98
     Quo
    0.97
    o
    0.95
     Ando
    0.95
    оо
    0.94
     Malo
    0.91
     Dodo
    0.91
     Puro
    0.91
    eco
    0.90
    Activations Density 1.174%

    No Known Activations