© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9842
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and API processes

    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
    Theorem
    -0.31
     darum
    -0.30
     journaux
    -0.29
     largely
    -0.28
     côtés
    -0.27
     Tapia
    -0.26
     villes
    -0.26
     boissons
    -0.26
     robust
    -0.26
     hoffen
    -0.26
    POSITIVE LOGITS
     reproduce
    0.93
     reproduction
    0.93
     expired
    0.91
     expire
    0.86
     expiration
    0.86
     Reproduction
    0.86
    complexContent
    0.85
    breeding
    0.85
     Breeding
    0.84
     reproducing
    0.84
    Activations Density 0.192%

    No Known Activations