© 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. 13957
    Prev
    Next
    INDEX
    Explanations

    references to specific baseball events and actions

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

    baseball-related statistics and game play descriptions.

    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
    ChildScrollView
    -0.77
     batting
    -0.58
     препратки
    -0.56
     batted
    -0.55
     resourceCulture
    -0.54
    astéroïdes
    -0.48
    rboles
    -0.46
     organisatie
    -0.45
    śle
    -0.44
    IContainer
    -0.44
    POSITIVE LOGITS
    QMetaType
    0.39
    \/
    0.35
    RefNanny
    0.34
     Reverso
    0.34
     Emp
    0.33
     guangdong
    0.33
    声
    0.33
    cpp
    0.33
     emp
    0.32
     Sus
    0.32
    Activations Density 0.034%

    No Known Activations