© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7052
    Prev
    Next
    INDEX
    Explanations

    programming constructs and file inclusions related to C/C++ code

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

    C/C++ preprocessor directives and header file inclusions.

    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
    Xna
    -0.59
     propOrder
    -0.56
     tslint
    -0.54
     otomatig
    -0.52
     valueOf
    -0.51
    SBATCH
    -0.51
    xhr
    -0.51
    RTSN
    -0.50
    PostBack
    -0.50
    tangentMode
    -0.50
    POSITIVE LOGITS
    setof
    0.43
     intptr
    0.43
    printf
    0.39
     menger
    0.36
    指针
    0.36
     NULL
    0.35
     portability
    0.35
     člá
    0.34
     segno
    0.33
    (*(
    0.32
    Activations Density 2.066%

    No Known Activations