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. 2-GEMMASCOPE-RES-16K
    6. 6571
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with specific geographic locations, names, and institutions

    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
     Punct
    -0.77
     Hendrix
    -0.74
     تانيه
    -0.72
    rú
    -0.71
     paraître
    -0.70
    Hend
    -0.67
     Washburn
    -0.66
    Sams
    -0.66
     dateTime
    -0.66
    allible
    -0.64
    POSITIVE LOGITS
     Twe
    1.00
     فريبيس
    0.95
     Lons
    0.88
     Brandi
    0.84
     Sarkozy
    0.83
     Osbourne
    0.82
    Twe
    0.82
     Depp
    0.81
     Auditor
    0.80
    clonal
    0.79
    Activations Density 8.490%

    No Known Activations