Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7400
    Prev
    Next
    INDEX
    Explanations

    terms related to health measurements and healthcare interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CharStream
    -0.42
     Min
    -0.39
    omo
    -0.39
     peculiarities
    -0.39
    original
    -0.38
     FRAMEWORK
    -0.38
    Beautifully
    -0.37
    История
    -0.37
     min
    -0.37
     ér
    -0.37
    POSITIVE LOGITS
     Efq
    0.86
     poffe
    0.86
     themſelves
    0.83
    
    0.81
     itſelf
    0.80
     Houſe
    0.79
     Majefty
    0.79
     تضيفلها
    0.79
     houſe
    0.76
     doubtnut
    0.76
    Activations Density 1.365%

    No Known Activations