© 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. 5-GEMMASCOPE-RES-16K
    6. 15088
    Prev
    Next
    INDEX
    Explanations

    key names and terms associated with medical conditions and health-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dab
    -1.04
     Dab
    -1.01
     FAB
    -0.98
    leb
    -0.96
     Gib
    -0.94
     Gub
    -0.93
    jab
    -0.93
    Jab
    -0.92
    dob
    -0.91
    Teb
    -0.90
    POSITIVE LOGITS
    gyz
    0.87
     spokoj
    0.80
    ContextHolder
    0.77
     AssemblyProduct
    0.76
     Fauci
    0.75
    หวัด
    0.74
     prince
    0.73
     PRINCE
    0.73
    Messi
    0.72
     Viti
    0.72
    Activations Density 1.890%

    No Known Activations