© 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. 3-GEMMASCOPE-RES-16K
    11. 8477
    Prev
    Next
    INDEX
    Explanations

    code structures and programming-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.91
     للاسماء
    -0.88
    PostInfinity
    -0.85
    expandindo
    -0.85
    setVerticalGroup
    -0.84
    bewerken
    -0.82
    ⓧ
    -0.82
     الحره
    -0.81
    errHandler
    -0.77
     MainAxisSize
    -0.77
    POSITIVE LOGITS
     promises
    0.35
     sides
    0.32
     pros
    0.31
     fast
    0.31
     fre
    0.31
     range
    0.31
     size
    0.30
     differently
    0.30
     form
    0.30
     定
    0.30
    Activations Density 1.522%

    No Known Activations