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. 14-GEMMASCOPE-RES-16K
    6. 93
    Prev
    Next
    INDEX
    Explanations

    references to specific temporal markers and milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.97
     okuyayım
    -0.85
    MigrationBuilder
    -0.85
     Roskov
    -0.85
    Билгалдахарш
    -0.82
     فريبيس
    -0.82
    rungsseite
    -0.81
     незавершена
    -0.77
     ddelweddau
    -0.76
     المعيارى
    -0.74
    POSITIVE LOGITS
     In
    0.72
    In
    0.69
     last
    0.62
     At
    0.58
     plus
    0.56
    At
    0.54
     By
    0.53
    View
    0.51
     general
    0.50
    By
    0.49
    Activations Density 0.190%

    No Known Activations