© 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. 10222
    Prev
    Next
    INDEX
    Explanations

    key terms related to personal identity and user privacy

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

    nouns and noun phrases that refer to specific entities, people, concepts, or objects.

    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
     Gelegenheit
    -0.52
     bagay
    -0.47
     coisa
    -0.44
     możliwe
    -0.43
    ंदीखरीदारी
    -0.43
     saites
    -0.40
     adicionales
    -0.39
     JADX
    -0.39
     Spannung
    -0.38
    zeba
    -0.38
    POSITIVE LOGITS
     arsenal
    0.62
     ambitions
    0.59
     préféré
    0.57
     obsession
    0.56
     signature
    0.56
     dealings
    0.55
     creations
    0.54
     counterparts
    0.54
     journey
    0.54
     repertoire
    0.54
    Activations Density 1.216%

    No Known Activations