© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 6953
    Prev
    Next
    INDEX
    Explanations

    specific author initials or designations in a scientific context

    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
    которые
    -1.14
    withstanding
    -0.83
    foundland
    -0.70
    tonsoft
    -0.68
    giveness
    -0.61
    ympto
    -0.58
    ergies
    -0.51
     ब्रेकडाउन
    -0.50
    YourGuide
    -0.48
    менно
    -0.47
    POSITIVE LOGITS
    nappropriate
    0.71
    достатки
    0.68
    tualmente
    0.67
    avadoc
    0.58
    guien
    0.57
    reamble
    0.57
    herited
    0.56
    ertia
    0.56
    SN
    0.56
    собенности
    0.55
    Activations Density 0.477%

    No Known Activations