© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11345
    Prev
    Next
    INDEX
    Explanations

    entities and terms related to the "tri-" prefix and its variations

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

    words beginning with "Tri" (three-letter prefix).

    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
    twimg
    -0.45
    endcsname
    -0.44
     Commencez
    -0.40
     FetchType
    -0.39
     دیکھیے
    -0.39
    міністра
    -0.38
     votación
    -0.38
     Jurí
    -0.37
     salvación
    -0.36
     Generales
    -0.36
    POSITIVE LOGITS
     Tri
    1.02
    Tri
    0.97
     tri
    0.90
    tri
    0.79
    setVerticalGroup
    0.70
     トリ
    0.70
     Trig
    0.69
     Trib
    0.68
     TRI
    0.65
     Три
    0.65
    Activations Density 0.164%

    No Known Activations