© 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. 40-GEMMASCOPE-RES-16K
    6. 5526
    Prev
    Next
    INDEX
    Explanations

    layout and styling properties in coding or programming languages

    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
    ruptedException
    -0.39
    consejos
    -0.36
    Amicalement
    -0.35
    Viungo
    -0.35
     次
    -0.33
    issä
    -0.32
     المعرف
    -0.32
     Dt
    -0.32
    ǒ
    -0.32
    #
    -0.32
    POSITIVE LOGITS
    rem
    0.66
    vw
    0.57
    em
    0.53
    vh
    0.50
    évaluateur
    0.49
    AddTagHelper
    0.48
    RenderAtEndOf
    0.48
    vmin
    0.47
    vmax
    0.46
    IUrlHelper
    0.45
    Activations Density 0.167%

    No Known Activations