© 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. 2137
    Prev
    Next
    INDEX
    Explanations

    references to games or playful activities

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

    the phrase "play the game" or similar idiomatic expressions using "play" with abstract nouns.

    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
     Codable
    -0.44
     nahilalakip
    -0.43
     unknownFields
    -0.42
     chi̍t
    -0.40
    OGND
    -0.39
    GEBURTS
    -0.38
     morado
    -0.37
    ineno
    -0.37
    OrBuilder
    -0.35
    IVEREF
    -0.35
    POSITIVE LOGITS
     playing
    1.69
     play
    1.59
    playing
    1.52
    Playing
    1.51
     game
    1.47
     Playing
    1.46
     played
    1.40
    play
    1.39
     juego
    1.38
     PLAYING
    1.31
    Activations Density 0.252%

    No Known Activations