© 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. 10233
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude or acknowledgment of contributions

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

    phrases where "for" is used to describe someone's notable qualities, achievements, or characteristics.

    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
    เอง
    -0.48
    __":
    -0.42
    __':
    -0.42
    Française
    -0.40
    comuna
    -0.40
    SaveChangesAsync
    -0.40
    uchin
    -0.39
    experienced
    -0.36
     ͜
    -0.36
     Gericht
    -0.36
    POSITIVE LOGITS
     being
    1.02
     having
    0.88
    being
    0.73
    Being
    0.70
    having
    0.68
     Мексичка
    0.68
     habiendo
    0.65
     HAVING
    0.65
     essere
    0.65
    Having
    0.65
    Activations Density 0.269%

    No Known Activations