© 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. 35-GEMMASCOPE-RES-16K
    11. 8381
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "cons," indicating uses related to concepts of conformity or consensus

    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
     betweenstory
    -0.57
     الرح
    -0.37
     cref
    -0.35
    Diam
    -0.35
     Diam
    -0.34
    abestanden
    -0.34
    oneofs
    -0.34
    InMillis
    -0.33
    loop
    -0.32
    twimg
    -0.32
    POSITIVE LOGITS
     Cons
    0.96
    Cons
    0.91
     cons
    0.89
    cons
    0.84
     Kons
    0.78
    Kons
    0.76
     kons
    0.74
     CONS
    0.73
     Consolidation
    0.70
     consolidation
    0.69
    Activations Density 0.241%

    No Known Activations