© 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. 3-GEMMASCOPE-RES-16K
    11. 8593
    Prev
    Next
    INDEX
    Explanations

    medical terminologies related to specific conditions and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Junta
    -0.39
     varandra
    -0.34
     geest
    -0.34
     Argent
    -0.33
     zas
    -0.33
     ре
    -0.31
    ösungen
    -0.31
     pagrind
    -0.31
    bahnen
    -0.31
    Prefer
    -0.31
    POSITIVE LOGITS
    ValueStyle
    0.77
    tagHelperRunner
    0.77
    tic
    0.75
     nahilalakip
    0.66
    AndEndTag
    0.64
    findpost
    0.62
    Penalty
    0.60
    penalty
    0.59
     attrs
    0.59
    TabIndex
    0.59
    Activations Density 1.214%

    No Known Activations