© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10038
    Prev
    Next
    INDEX
    Explanations

    references to small populations or minority groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ivelany
    -0.82
     AssemblyCulture
    -0.76
     незавершена
    -0.71
    SequentialGroup
    -0.71
    MessageTagHelper
    -0.69
    adpleegd
    -0.64
    abetes
    -0.61
    MigrationBuilder
    -0.60
    клопе
    -0.60
    цездатний
    -0.60
    POSITIVE LOGITS
     rare
    1.05
     few
    0.96
    rare
    0.93
    Rare
    0.92
    少数
    0.92
     handful
    0.90
     Rare
    0.88
     limited
    0.88
     rares
    0.87
     pocos
    0.87
    Activations Density 0.629%

    No Known Activations