© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12759
    Prev
    Next
    INDEX
    Explanations

    terms related to post-event effects and medical outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases involving "post-" (post-election, post-stroke, post-transplant, etc.).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.35
    UY
    -0.33
     ſte
    -0.33
    impresa
    -0.33
    RequestType
    -0.33
    createStatement
    -0.33
    EE
    -0.33
    𝐗
    -0.33
     unto
    -0.32
     rolled
    -0.32
    POSITIVE LOGITS
     after
    1.05
     после
    0.98
     після
    0.95
    after
    0.94
    After
    0.93
     After
    0.92
     après
    0.91
     AFTER
    0.91
     efter
    0.89
     após
    0.89
    Activations Density 0.187%

    No Known Activations