© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 12404
    Prev
    Next
    INDEX
    Explanations

    sequences of genetic material denoted by the letter "A"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tualmente
    -0.75
    hogy
    -0.74
    d
    -0.60
    n
    -0.57
    t
    -0.53
    c
    -0.47
    m
    -0.46
    l
    -0.46
    guien
    -0.46
    hem
    -0.45
    POSITIVE LOGITS
    structors
    0.73
    withstanding
    0.70
    nemia
    0.67
    ergies
    0.66
    tably
    0.66
    poptosis
    0.65
    volvement
    0.64
    queous
    0.63
    hibition
    0.61
    warded
    0.61
    Activations Density 0.207%

    No Known Activations