© 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. 22-GEMMASCOPE-RES-16K
    11. 5177
    Prev
    Next
    INDEX
    Explanations

    phrases and statistics related to prevalence and majority in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewDid
    -0.44
     مرئيه
    -0.40
     fark
    -0.40
     ModelExpression
    -0.38
     conjun
    -0.36
     mutu
    -0.36
    phem
    -0.36
     múl
    -0.35
     calle
    -0.35
     silic
    -0.34
    POSITIVE LOGITS
     majority
    0.77
     maioria
    0.69
    Majority
    0.67
     Majority
    0.66
     sebagian
    0.66
    majority
    0.65
     plupart
    0.63
     cases
    0.63
     vět
    0.62
     Occasionally
    0.61
    Activations Density 0.967%

    No Known Activations