© 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. 9976
    Prev
    Next
    INDEX
    Explanations

    parameter names and properties related to dimensional attributes in coding

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

    numeric literals and coordinate values in 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
     تضيفلها
    -0.96
    AndEndTag
    -0.91
     ſehr
    -0.85
     defaultstate
    -0.82
     zwiſchen
    -0.81
     queſta
    -0.81
     témoig
    -0.79
     zuſammen
    -0.78
     beſch
    -0.78
    IntoConstraints
    -0.77
    POSITIVE LOGITS
     +
    0.61
     >
    0.43
     /
    0.40
     -
    0.39
    +
    0.38
     without
    0.37
     +=
    0.36
     rather
    0.35
     instead
    0.34
     >=
    0.33
    Activations Density 0.520%

    No Known Activations