© 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. 15236
    Prev
    Next
    INDEX
    Explanations

    friendly expressions and topics related to crafting or DIY projects

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

    expressions of gratitude and appreciation.

    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
    UseVisualStyle
    -0.46
    GEBURTS
    -0.39
    Хьажоргаш
    -0.38
    还不是
    -0.38
     Specialists
    -0.37
    UpInside
    -0.36
    SequentialGroup
    -0.35
    TintMode
    -0.35
    prepareStatement
    -0.35
     basically
    -0.34
    POSITIVE LOGITS
     congrats
    0.79
     excellent
    0.77
    Excellent
    0.73
    Congrats
    0.73
     congratulations
    0.72
     Congrats
    0.72
    excellent
    0.71
    Nice
    0.71
    Congratulations
    0.70
     Excellent
    0.68
    Activations Density 0.190%

    No Known Activations