© 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. 31-GEMMASCOPE-RES-16K
    11. 15624
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with individuals or entities in a formal context

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

    names of people followed by a comma or dash in formal document headers and bylines.

    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
     Chwiliwch
    -0.96
     disambiguazione
    -0.84
    astéroïdes
    -0.80
     nahilalakip
    -0.79
    GEBURTSDATUM
    -0.76
     للاسماء
    -0.71
    featureID
    -0.70
    RenderAtEndOf
    -0.69
    각주
    -0.69
    rungsseite
    -0.68
    POSITIVE LOGITS
     Jr
    0.77
     Esq
    0.73
     PhD
    0.71
     CEO
    0.62
     assistant
    0.61
     Senior
    0.61
     Director
    0.59
     senior
    0.59
     president
    0.59
     director
    0.57
    Activations Density 0.674%

    No Known Activations