© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11046
    Prev
    Next
    INDEX
    Explanations

    JavaScript and SQL function syntax related to player actions in a game

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.75
     consultato
    -0.61
    intios
    -0.61
     חיצוניים
    -0.56
     Wicidata
    -0.53
     indisponible
    -0.52
     Photocase
    -0.50
     commission
    -0.50
    commission
    -0.49
    rawdę
    -0.49
    POSITIVE LOGITS
     player
    3.26
    player
    2.99
     Player
    2.47
    Player
    2.33
     patient
    2.28
     PLAYER
    2.10
     student
    1.95
    patient
    1.95
    PLAYER
    1.88
     jugador
    1.81
    Activations Density 0.240%

    No Known Activations