© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7792
    Prev
    Next
    INDEX
    Explanations

    coding syntax and structure within a programming context

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

    Code accessing game object instances

    np_acts-logits-general · gemini-2.0-flash

    game AI actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.40
     universidades
    -0.35
    Closure
    -0.35
     affari
    -0.34
     corporate
    -0.32
     aziende
    -0.32
     dates
    -0.32
     closure
    -0.31
     Paglinawan
    -0.31
    express
    -0.31
    POSITIVE LOGITS
     ingame
    0.80
    gameserver
    0.71
     player
    0.71
     NPCs
    0.70
     NPC
    0.67
     gameplay
    0.66
     joueur
    0.65
    NPC
    0.65
     scripted
    0.63
     Gameplay
    0.62
    Activations Density 0.911%

    No Known Activations