© 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. 8417
    Prev
    Next
    INDEX
    Explanations

    keywords and terms related to programming standards and structures

    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
    ьаж
    -0.47
    adpleegd
    -0.47
     gastronom
    -0.42
    featureID
    -0.42
     Matter
    -0.40
     Ты
    -0.40
     Objection
    -0.39
    ſelf
    -0.39
     OGSÅ
    -0.39
    Koordinaten
    -0.39
    POSITIVE LOGITS
     Traditional
    0.98
    Traditional
    0.92
    Original
    0.91
    Static
    0.90
     Original
    0.89
    Natural
    0.89
     Natural
    0.88
     Personal
    0.88
    Simple
    0.87
     Special
    0.85
    Activations Density 0.449%

    No Known Activations