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. 7114
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue within the text

    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
     $.
    -0.33
     mecán
    -0.30
    日閲覧
    -0.30
     跳转至
    -0.30
     Namely
    -0.29
     ویکی‌پدیای
    -0.29
     $
    -0.29
     MediatR
    -0.28
     equally
    -0.28
     ${\
    -0.28
    POSITIVE LOGITS
    use
    0.79
    Tis
    0.60
    findpost
    0.59
    Twas
    0.55
    MessageOf
    0.54
     uid
    0.52
    />
    0.51
     width
    0.51
    tanleria
    0.50
     />
    0.50
    Activations Density 0.290%

    No Known Activations