© 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. 12425
    Prev
    Next
    INDEX
    Explanations

    coding and programming-related syntax and structure

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

    C/C++ code syntax and structural elements like variable declarations, function calls, pointer operations, and network programming constructs.

    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
    msgTypes
    -0.40
     late
    -0.36
     CWE
    -0.35
     сторо
    -0.33
    Referințe
    -0.32
     bulu
    -0.32
     pel
    -0.32
     fur
    -0.31
    GridColumn
    -0.31
    mut
    -0.31
    POSITIVE LOGITS
     endian
    0.66
    Little
    0.65
    LITTLE
    0.63
    little
    0.62
     LITTLE
    0.59
     Little
    0.58
    endian
    0.57
     propOrder
    0.56
    mybatisplus
    0.54
     AssemblyVersion
    0.54
    Activations Density 0.738%

    No Known Activations