© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3446
    Prev
    Next
    INDEX
    Explanations

    mentions of runners and related terms in a sporting or competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     workshop
    -0.37
     Milestone
    -0.35
     Mus
    -0.34
     bowl
    -0.33
     Tremb
    -0.33
    __()
    -0.32
     chimney
    -0.32
    SPATH
    -0.32
     szé
    -0.32
     bim
    -0.32
    POSITIVE LOGITS
     Federation
    0.84
     Fed
    0.82
    Federation
    0.81
    Feder
    0.80
    SequentialGroup
    0.77
     Feder
    0.77
     FED
    0.76
     feder
    0.75
     federation
    0.75
    feder
    0.73
    Activations Density 0.208%

    No Known Activations