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. 0-GEMMASCOPE-RES-16K
    6. 8325
    Prev
    Next
    INDEX
    Explanations

    references to Africa and related cultural or demographic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QMetaType
    -0.59
    ânico
    -0.56
    ::::::::::::::::
    -0.53
     alimen
    -0.53
     Sumit
    -0.53
    Tito
    -0.52
     bivolt
    -0.51
    assination
    -0.51
     Mox
    -0.50
     }{@
    -0.50
    POSITIVE LOGITS
     Africa
    1.16
     African
    1.15
    African
    1.11
     AFRICAN
    1.08
    Africa
    1.03
     Nigerian
    0.99
     AFRICA
    0.98
     África
    0.97
     Nigeria
    0.96
     african
    0.95
    Activations Density 2.940%

    No Known Activations