© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 8557
    Prev
    Next
    INDEX
    Explanations

    references to the concept of consistency

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    consistency check and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     насељу
    -0.63
    SBATCH
    -0.57
    waltung
    -0.52
    cetype
    -0.50
    pageX
    -0.50
    elfare
    -0.50
     informée
    -0.50
     láser
    -0.48
    bkz
    -0.48
    Katso
    -0.48
    POSITIVE LOGITS
     consistency
    1.97
     Consistency
    1.88
    Consistency
    1.79
    consistency
    1.77
     consistent
    1.54
     Consistent
    1.48
    consistent
    1.48
     inconsistency
    1.45
    Consistent
    1.41
     inconsistent
    1.31
    Activations Density 0.016%

    No Known Activations