© 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. 40-GEMMASCOPE-RES-16K
    11. 2036
    Prev
    Next
    INDEX
    Explanations

    acknowledgment and references to organizations or contributions in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Brand
    -0.42
    엌
    -0.41
    Πηγές
    -0.39
     incluidas
    -0.39
     deberes
    -0.37
     ruler
    -0.37
    buz
    -0.36
     vuestros
    -0.36
     viñ
    -0.36
     opat
    -0.35
    POSITIVE LOGITS
    ViewInit
    0.55
    AnchorStyles
    0.50
    mobileqq
    0.46
    exitRule
    0.45
    avadoc
    0.44
    ウンサー
    0.43
     hed
    0.43
    IsMutable
    0.41
    Insee
    0.41
     creat
    0.41
    Activations Density 0.089%

    No Known Activations