© 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. 23-GEMMASCOPE-RES-16K
    11. 10598
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    省市镇
    -0.44
    tigste
    -0.40
    帖最后由
    -0.38
    IGENCE
    -0.35
    RectangleBorder
    -0.35
     основ
    -0.35
     solange
    -0.34
     enough
    -0.34
     Trans
    -0.33
    hmigung
    -0.33
    POSITIVE LOGITS
    DeleteBehavior
    0.57
     insistence
    0.54
    новништво
    0.54
     pouvoit
    0.54
     avoient
    0.52
     uſed
    0.51
     raiſ
    0.51
    msgTypes
    0.50
     {}),
    0.50
     uſe
    0.49
    Activations Density 0.767%

    No Known Activations