© 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. 6-GEMMASCOPE-RES-16K
    6. 5456
    Prev
    Next
    INDEX
    Explanations

    phrases indicating interaction and relationships between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zd
    -0.66
     tetto
    -0.65
    ншни
    -0.61
     vägen
    -0.59
    ']==
    -0.58
     sonno
    -0.56
     fous
    -0.56
     тому
    -0.56
     Vod
    -0.56
    луй
    -0.55
    POSITIVE LOGITS
     interaction
    2.05
     interactions
    2.04
     Interaction
    1.99
     Interactions
    1.93
    Interaction
    1.86
    interaction
    1.84
     interact
    1.81
    Interactions
    1.79
     Interact
    1.76
    interactions
    1.76
    Activations Density 0.074%

    No Known Activations