© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3372
    Prev
    Next
    INDEX
    Explanations

    medical terminology and phrases related to neurological conditions and their evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rehearing
    -0.52
     BoxFit
    -0.51
     dépasse
    -0.51
     vergeten
    -0.49
    SPJ
    -0.47
     femeninos
    -0.47
    Arbitrage
    -0.46
     bellissimo
    -0.45
     perjury
    -0.45
     mío
    -0.45
    POSITIVE LOGITS
     amount
    1.64
     extent
    1.53
     degree
    1.40
     size
    1.31
    amount
    1.24
     nature
    1.18
     number
    1.17
     length
    1.16
     how
    1.15
     severity
    1.14
    Activations Density 0.832%

    No Known Activations