© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 3374
    Prev
    Next
    INDEX
    Explanations

    references to the concept of lateness or timing, particularly the word "late" and its variations

    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
     виправивши
    -1.04
     Roskov
    -0.94
    complexContent
    -0.92
    ècie
    -0.90
     referenties
    -0.90
     Brugge
    -0.89
     ویکی‌پدیای
    -0.87
    #+#
    -0.86
    ثيق
    -0.86
    +#+#
    -0.85
    POSITIVE LOGITS
     LATE
    1.60
     Late
    1.51
    LATE
    1.44
    Late
    1.40
     late
    1.38
    late
    1.14
     Early
    0.97
    Early
    0.92
     EARLY
    0.91
    EARLY
    0.90
    Activations Density 0.057%

    No Known Activations