© 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. 31-GEMMASCOPE-RES-16K
    11. 2958
    Prev
    Next
    INDEX
    Explanations

    components and methods related to game entity management and interaction within a programming context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    object instances and method calls on those instances in Java code.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     iſt
    -0.64
    IUrlHelper
    -0.63
     onCreateView
    -0.62
    parsedMessage
    -0.60
     otomatig
    -0.60
    chyma
    -0.60
     esternos
    -0.60
     Efq
    -0.60
    Obrázky
    -0.59
    ſhip
    -0.59
    POSITIVE LOGITS
    .
    0.77
    ’
    0.40
    cemment
    0.40
    '
    0.39
     द्वारा
    0.39
     Frucht
    0.38
    Instance
    0.35
     will
    0.35
     tarafından
    0.35
    begin
    0.34
    Activations Density 0.231%

    No Known Activations