© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14932
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical conditions and their evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    ValueStyle
    -0.72
    Hauptartikel
    -0.52
     jotka
    -0.52
    RetentionPolicy
    -0.50
     fallu
    -0.49
     foncé
    -0.47
     когато
    -0.45
     egli
    -0.44
    什么是
    -0.44
     وتسجيلات
    -0.44
    POSITIVE LOGITS
     able
    1.05
     unable
    0.97
     extremely
    0.94
     very
    0.91
     not
    0.90
     unlikely
    0.90
     considered
    0.88
     quite
    0.85
     liable
    0.85
     difficult
    0.84
    Activations Density 0.560%

    No Known Activations