Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 12702
    Prev
    Next
    INDEX
    Explanations

    references to fractions or partial quantities, particularly "half"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="#"><
    -0.85
     وتسجيلات
    -0.84
    Bibliographie
    -0.84
    })));
    -0.79
    validates
    -0.75
    AMAZ
    -0.74
     Davie
    -0.73
     Mercurio
    -0.72
    mobileqq
    -0.72
    neous
    -0.71
    POSITIVE LOGITS
     half
    1.60
     Half
    1.55
    Half
    1.48
    half
    1.47
     HALF
    1.45
    HALF
    1.29
     halves
    1.25
    半
    1.00
     metade
    0.96
     Hälfte
    0.93
    Activations Density 0.141%

    No Known Activations