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

    Neuronpedia

    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. 6126
    Prev
    Next
    INDEX
    Explanations

    topics related to medical conditions and their assessment challenges

    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
     Keim
    -0.26
    プリング
    -0.25
    チール
    -0.25
    zi
    -0.25
    iorna
    -0.24
     شعار
    -0.24
    shame
    -0.23
     Pas
    -0.23
     kep
    -0.23
    ニーカー
    -0.22
    POSITIVE LOGITS
     poses
    2.28
     pose
    2.19
     posing
    1.95
     posed
    1.93
     Pose
    1.79
    poses
    1.66
     presents
    1.60
    pose
    1.55
    Pose
    1.53
    presents
    1.41
    Activations Density 0.991%

    No Known Activations