© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 13260
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and regulatory topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ised
    -1.00
    StateToProps
    -0.80
    ième
    -0.79
    tól
    -0.79
    ians
    -0.77
    ۰
    -0.73
    ový
    -0.72
    י
    -0.67
    ação
    -0.67
    ology
    -0.67
    POSITIVE LOGITS
    devo
    0.47
    pop
    0.47
    kram
    0.46
    urb
    0.46
     Utf
    0.45
    ை
    0.44
    ▬
    0.44
    te
    0.43
    न
    0.43
    ്‍
    0.42
    Activations Density 3.131%

    No Known Activations