© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 7645
    Prev
    Next
    INDEX
    Explanations

    phrases involving sets, intersections, and comparisons

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

    comparisons or contrasts between two items or groups.

    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
    Seven
    -0.45
    ?,?,
    -0.45
    Nine
    -0.45
     siete
    -0.43
    werfer
    -0.42
     Nine
    -0.42
    Thirteen
    -0.41
    Eight
    -0.41
     Eight
    -0.40
     otto
    -0.39
    POSITIVE LOGITS
     two
    2.92
    two
    2.38
     deux
    2.33
     zwei
    2.13
    Two
    2.00
     två
    2.00
    两个
    1.97
     duas
    1.91
     két
    1.90
     zweier
    1.90
    Activations Density 1.583%

    No Known Activations