© 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. 10309
    Prev
    Next
    INDEX
    Explanations

    keywords and objects related to programming constructs and data structures in code

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

    multi-word compound identifiers and class/function names in source code.

    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
     Beſ
    -0.62
     ainfi
    -0.59
     ब्रेकडाउन
    -0.57
     auroit
    -0.54
     étoient
    -0.53
    PYX
    -0.51
    AnchorStyles
    -0.51
    iſter
    -0.50
     feroit
    -0.49
     avoient
    -0.49
    POSITIVE LOGITS
     tiểu
    0.44
    elemField
    0.39
     integral
    0.37
     onPause
    0.37
     weg
    0.35
    LLocation
    0.35
     recognition
    0.35
    recognition
    0.34
    hasNext
    0.33
    agonal
    0.33
    Activations Density 0.686%

    No Known Activations