© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8720
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to web development frameworks and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.56
    ロウィン
    -0.51
     comuniques
    -0.48
    ❈
    -0.48
    zeera
    -0.47
     batt
    -0.46
     Gamma
    -0.46
     esti
    -0.46
    atural
    -0.45
    飛ば
    -0.45
    POSITIVE LOGITS
    
    0.71
    bootstrapcdn
    0.41
    CodeAttribute
    0.41
     techniczne
    0.41
     autory
    0.41
    hörigen
    0.41
     especializado
    0.40
    iostream
    0.40
     especializados
    0.40
     sterile
    0.40
    Activations Density 1.909%

    No Known Activations