© 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. 5174
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures

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

    uppercase identifier patterns commonly found in code macros and constants.

    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
     protoimpl
    -0.75
     ***!
    -0.70
    MigrationBuilder
    -0.68
     deſſen
    -0.64
    saraba
    -0.63
    ScopeManager
    -0.59
    󠁣
    -0.59
     aguja
    -0.57
    Rhestr
    -0.56
    ymce
    -0.56
    POSITIVE LOGITS
    _
    0.41
     utafitiHapana
    0.37
     Kanada
    0.37
    XS
    0.36
     somewhat
    0.35
     Indon
    0.35
    Fortunately
    0.35
     Viitattu
    0.32
    Thankfully
    0.32
    XD
    0.32
    Activations Density 0.873%

    No Known Activations