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

    Neuronpedia

    Jacobian LensNEW
    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. 35-GEMMASCOPE-RES-16K
    11. 11874
    Prev
    Next
    INDEX
    Explanations

    complex and nuanced discussions about social and economic themes, particularly around fairness, classification, and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Yet
    -0.90
     Yet
    -0.86
     entanto
    -0.85
     pourtant
    -0.82
     However
    -0.81
     however
    -0.81
     yet
    -0.79
     kuitenkin
    -0.79
    However
    -0.78
     nevertheless
    -0.76
    POSITIVE LOGITS
     sondern
    1.24
     hanem
    1.07
    而是
    1.04
     بلکه
    1.04
     sino
    1.02
     אלא
    0.91
     vaan
    0.88
     melainkan
    0.87
     utan
    0.76
     necessarily
    0.75
    Activations Density 0.235%

    No Known Activations