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. 23-GEMMASCOPE-RES-16K
    6. 5101
    Prev
    Next
    INDEX
    Explanations

    terms related to software licensing and legal compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一定要
    -0.47
    فية
    -0.47
    Most
    -0.46
    тесь
    -0.46
    ToDate
    -0.46
     dis
    -0.46
    ster
    -0.46
    And
    -0.45
    abilirsiniz
    -0.45
    cont
    -0.45
    POSITIVE LOGITS
    Rüyada
    1.09
    BeginContext
    0.97
     فريبيس
    0.95
    Personensuche
    0.94
     متعلقه
    0.93
    EDEFAULT
    0.92
     kasarigan
    0.91
    Geplaatst
    0.88
    GEBURTSDATUM
    0.86
    TagMode
    0.85
    Activations Density 0.737%

    No Known Activations