© 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. 5454
    Prev
    Next
    INDEX
    Explanations

    snippets of code or programming structures

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

    structural elements and keywords in code like closing braces, access modifiers (private, public, static), and whitespace/indentation patterns.

    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
    断
    -0.28
     silently
    -0.27
    lably
    -0.27
     YO
    -0.27
     newArray
    -0.26
    MenuInflater
    -0.26
     mona
    -0.25
     Ress
    -0.25
    茅
    -0.24
     Auff
    -0.24
    POSITIVE LOGITS
    Viited
    0.71
    late
    0.66
    final
    0.64
     للاسماء
    0.63
     surla
    0.62
    Hentet
    0.61
     late
    0.61
    bool
    0.59
    fitrión
    0.57
    CppMethod
    0.57
    Activations Density 0.041%

    No Known Activations