© 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. 33-GEMMASCOPE-RES-16K
    6. 11779
    Prev
    Next
    INDEX
    Explanations

    variables and mathematical notation elements in equations and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.66
    windowFixed
    -0.61
    ьаж
    -0.57
    Personensuche
    -0.53
    ‌شده
    -0.52
     unterkunft
    -0.52
     "..\..\..\
    -0.51
     AllAfrica
    -0.50
    expandindo
    -0.50
     linkovi
    -0.48
    POSITIVE LOGITS
     ๆ
    0.49
    赂
    0.46
     chat
    0.45
     Spring
    0.45
     config
    0.44
     typ
    0.44
     sum
    0.44
     spring
    0.43
     Berger
    0.43
     type
    0.43
    Activations Density 0.941%

    No Known Activations