© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 90546
    Prev
    Next
    INDEX
    Explanations

    references to player development and youth teams in sports

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

    new beginnings or debut

    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
    #+#
    -0.39
    UnitTesting
    -0.37
    wendige
    -0.34
    XmlIgnore
    -0.34
    悻
    -0.32
     noDo
    -0.31
    Quest
    -0.31
    
    -0.31
    page
    -0.30
    FormState
    -0.30
    POSITIVE LOGITS
     debut
    0.62
     varsity
    0.61
     debuts
    0.61
    rawDesc
    0.61
    senior
    0.59
     senior
    0.57
    昇
    0.57
     main
    0.56
    GIVEREF
    0.56
    升
    0.55
    Activations Density 0.036%

    No Known Activations