© 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. 4716
    Prev
    Next
    INDEX
    Explanations

    programming terms related to syntax and structure in code

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

    whitespace and spacing characters, particularly in contexts involving alignment, formatting, or precise character positioning.

    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
    SOUNDBITE
    -0.54
    ExecuteReader
    -0.44
     Efq
    -0.41
    AccessorTable
    -0.40
    Становништво
    -0.40
    EDEFAULT
    -0.39
    featureID
    -0.39
    enterOuterAlt
    -0.37
    HasAnnotation
    -0.37
    TagMode
    -0.36
    POSITIVE LOGITS
     preceding
    1.27
     preceded
    1.13
     before
    1.12
     precedes
    1.10
     after
    1.07
     precede
    1.06
    before
    1.01
     précé
    0.99
    after
    0.96
     AFTER
    0.93
    Activations Density 1.089%

    No Known Activations