© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14447
    Prev
    Next
    INDEX
    Explanations

    references to contextual settings or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sexuales
    -0.71
     laiton
    -0.66
     negras
    -0.62
     Advancement
    -0.60
     sauvages
    -0.60
     fuite
    -0.60
     rechange
    -0.59
     honte
    -0.57
     automatiques
    -0.56
     commerciales
    -0.56
    POSITIVE LOGITS
     environment
    1.37
     context
    1.36
     environments
    1.25
     contexts
    1.22
     surroundings
    1.15
     circumstances
    1.13
     Environment
    1.10
     backdrop
    1.08
     contesto
    1.08
     entorno
    1.05
    Activations Density 0.380%

    No Known Activations