© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3227
    Prev
    Next
    INDEX
    Explanations

    elements related to comparison and dichotomy in musical and entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing contrasts or comparisons between different characteristics or entities.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.44
    ativement
    -0.38
     migliore
    -0.38
     lanterna
    -0.38
     migli
    -0.37
     najleps
    -0.36
    LayoutStyle
    -0.36
    Invalidate
    -0.35
     mejor
    -0.35
    eadilan
    -0.35
    POSITIVE LOGITS
     conservative
    1.00
     quiet
    0.93
     quieter
    0.90
     mellow
    0.90
     austere
    0.90
     calm
    0.89
    conservative
    0.89
     softer
    0.88
     somber
    0.88
     calmer
    0.86
    Activations Density 0.613%

    No Known Activations