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. 1-GEMMASCOPE-RES-16K
    6. 13565
    Prev
    Next
    INDEX
    Explanations

    repeated references to the term "South" or "South Africa."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.71
     JpaRepository
    -0.66
     typelib
    -0.64
    Brainz
    -0.63
     chanter
    -0.61
    rmızı
    -0.61
    irability
    -0.61
     通販
    -0.58
    ➽
    -0.57
    Druid
    -0.56
    POSITIVE LOGITS
     South
    1.33
    South
    1.24
     SA
    1.03
     SOUTH
    1.00
    south
    0.83
    SA
    0.82
     Saudi
    0.80
    SOUTH
    0.75
    Saudi
    0.63
    outh
    0.63
    Activations Density 0.109%

    No Known Activations