© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8830
    Prev
    Next
    INDEX
    Explanations

    punctuated statements or phrases indicating opinions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    But
    -1.00
    BUT
    -0.98
     BUT
    -0.94
     porém
    -0.88
    Yet
    -0.88
     Però
    -0.87
    However
    -0.86
     però
    -0.85
     But
    -0.85
     однако
    -0.85
    POSITIVE LOGITS
     bu
    0.63
     OFDb
    0.53
    튿
    0.47
    存档备份
    0.46
     buy
    0.46
    قایناقلار
    0.46
    maquilla
    0.46
     bit
    0.45
    Vastaa
    0.45
     bụ
    0.45
    Activations Density 0.271%

    No Known Activations