© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13470
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and risks associated with interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ][-
    -0.28
    チール
    -0.27
    マンド
    -0.26
    aż
    -0.25
     Keim
    -0.25
    ิส
    -0.24
     bâton
    -0.24
     Knapp
    -0.23
     kep
    -0.23
    zi
    -0.23
    POSITIVE LOGITS
     poses
    2.38
     pose
    2.27
     posed
    2.00
     posing
    2.00
     Pose
    1.86
     presents
    1.73
    poses
    1.66
    pose
    1.58
    Pose
    1.55
    presents
    1.52
    Activations Density 0.828%

    No Known Activations