© 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. 2-GEMMASCOPE-RES-16K
    6. 6023
    Prev
    Next
    INDEX
    Explanations

    specific terms related to health and fitness, particularly focusing on assessments and activities related to physical exertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Atkinson
    -0.85
     Cleary
    -0.74
     Goode
    -0.74
     Gurney
    -0.74
     Whitaker
    -0.73
    princ
    -0.72
     Hernando
    -0.71
     Cutler
    -0.71
     Vere
    -0.71
     Sond
    -0.71
    POSITIVE LOGITS
     Borg
    0.93
     pond
    0.85
    BeginContext
    0.85
    setViewportView
    0.79
    Borg
    0.79
    PageIndex
    0.78
    Pond
    0.77
    Coven
    0.75
    pond
    0.74
    Collegamenti
    0.73
    Activations Density 8.993%

    No Known Activations