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. 10-GEMMASCOPE-RES-16K
    6. 2623
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.61
    .
    -0.57
    ↵
    -0.55
    нс
    -0.50
    ↵↵↵
    -0.49
    ↵↵↵↵
    -0.49
    ?
    -0.48
    <eos>
    -0.45
    mcg
    -0.45
    {{
    -0.44
    POSITIVE LOGITS
     propOrder
    1.23
     nahilalakip
    1.13
     autorytatywna
    1.00
    fromnode
    0.98
    InjectAttribute
    0.98
     initComponents
    0.97
    Personendaten
    0.91
    AddHtmlAttribute
    0.88
    AccessorTable
    0.85
    GEBURTSDATUM
    0.85
    Activations Density 0.176%

    No Known Activations