Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 10656
    Prev
    Next
    INDEX
    Explanations

    intensely negative or critical descriptions

    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
     Photocase
    -0.49
    ‍♀️
    -0.48
    orship
    -0.46
    iteration
    -0.46
    tioner
    -0.45
    hacer
    -0.43
     fleste
    -0.43
    hilation
    -0.43
    Välislingid
    -0.41
    arised
    -0.41
    POSITIVE LOGITS
    ly
    3.88
    LY
    2.31
    mente
    1.66
    lye
    1.50
    lyt
    1.33
    lyl
    1.27
    lyse
    1.23
    lyon
    1.19
    lya
    1.11
    lyk
    1.10
    Activations Density 0.875%

    No Known Activations