© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 24161
    Prev
    Next
    INDEX
    Explanations

    references to cultural or religious celebrations

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

    symbolic / paint / red / trigger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     indépendant
    -0.36
     qualquer
    -0.35
    theoremstyle
    -0.35
     věci
    -0.35
    MathML
    -0.33
     cualquier
    -0.33
     conviene
    -0.33
     indépendante
    -0.32
     inmediata
    -0.32
    发表于
    -0.32
    POSITIVE LOGITS
     symbolically
    1.17
     symbo
    1.14
     symbolic
    1.12
    symbolic
    1.00
     simbo
    0.93
     symbolizes
    0.91
     symboli
    0.90
     simb
    0.90
     symbolize
    0.87
     symbol
    0.86
    Activations Density 0.035%

    No Known Activations