© 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. 15123
    Prev
    Next
    INDEX
    Explanations

    codes and technical specifications related to data or software

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

    hexadecimal codes and memory addresses in technical/binary data structures.

    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
    IsUnicode
    -0.57
     MainAxisSize
    -0.50
    copg
    -0.50
    WebpackPlugin
    -0.49
    
    -0.48
    useNewUrlParser
    -0.48
    nextDouble
    -0.47
    UserScript
    -0.45
    AddWithValue
    -0.44
     NSCoder
    -0.44
    POSITIVE LOGITS
     F
    1.08
     f
    0.85
    F
    0.79
     FS
    0.75
     FM
    0.75
     ف
    0.73
     FV
    0.72
     FH
    0.72
     FF
    0.71
     FP
    0.71
    Activations Density 2.045%

    No Known Activations