© 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. 1-GEMMASCOPE-RES-16K
    11. 4008
    Prev
    Next
    INDEX
    Explanations

    references to numbers, particularly three's

    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
     Pliny
    -0.83
     RSSSF
    -0.77
     Majefty
    -0.72
     humain
    -0.69
     Pilate
    -0.68
     lyre
    -0.68
     vectorielles
    -0.68
     Plutarch
    -0.67
     espagne
    -0.67
     Assyrian
    -0.66
    POSITIVE LOGITS
     three
    2.98
     four
    2.76
     two
    2.63
    three
    2.50
     five
    2.46
     trois
    2.27
     THREE
    2.17
     Three
    2.16
    two
    2.15
    four
    2.15
    Activations Density 0.181%

    No Known Activations