© 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. 33-GEMMASCOPE-RES-16K
    11. 7079
    Prev
    Next
    INDEX
    Explanations

    elements of structured data or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.61
     فريبيس
    -0.61
     resourceCulture
    -0.61
    MigrationBuilder
    -0.56
     Jefus
    -0.50
     Administrativna
    -0.50
    AutoField
    -0.50
    GIVEREF
    -0.50
     fevere
    -0.49
    ̈́
    -0.48
    POSITIVE LOGITS
     thirteenth
    0.91
     thirteen
    0.89
     Thirteen
    0.86
     fourteen
    0.85
     fourteenth
    0.83
     twelfth
    0.82
    Thirteen
    0.81
     twelve
    0.81
     Thirteenth
    0.80
    十三
    0.79
    Activations Density 1.010%

    No Known Activations