© 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. 2-GEMMASCOPE-RES-16K
    11. 8490
    Prev
    Next
    INDEX
    Explanations

    terminology related to compromise and components in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.67
    tvguidetime
    -0.58
    httphttps
    -0.55
     BoxDecoration
    -0.53
     ligiloj
    -0.50
    scriptcase
    -0.50
     AssemblyCulture
    -0.49
     initComponents
    -0.49
    Портал
    -0.48
    ьаж
    -0.47
    POSITIVE LOGITS
    comprom
    0.76
     compromise
    0.71
     comprise
    0.70
     compromising
    0.69
     comprises
    0.68
     compromised
    0.66
     Comprom
    0.65
     comprom
    0.63
     compromises
    0.62
    them
    0.61
    Activations Density 0.143%

    No Known Activations