© 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. 31-GEMMASCOPE-RES-16K
    6. 12736
    Prev
    Next
    INDEX
    Explanations

    negations and contractions in statements

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

    contractions with apostrophes, particularly in negative forms like "didn't," "won't," "isn't," and "hasn't."

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.75
    ViewImports
    -0.64
    fjspx
    -0.62
    游戏亮点
    -0.60
    WebVitals
    -0.56
    principalTable
    -0.54
     TextInputType
    -0.53
     ब्रेकडाउन
    -0.52
    optionalTypeArgs
    -0.52
    BufferException
    -0.52
    POSITIVE LOGITS
    -------
    
    0.44
     |
    
    0.38
    "])
    
    0.36
    "}"
    0.36
    ']):
    0.36
    :\\
    0.35
    -),
    0.35
    ‑
    0.35
    -)
    0.35
     Seiz
    0.35
    Activations Density 0.214%

    No Known Activations