© 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-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12471
    Prev
    Next
    INDEX
    Explanations

    key terms related to historical events and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding "the" or related to Viking/Saxon history

    np_acts-logits-general · gemini-2.0-flash

    Viking chieftain Olaf

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.57
     bayonet
    -0.54
    XmlRootElement
    -0.52
    addGap
    -0.47
    MemoryWarning
    -0.46
    ArgsConstructor
    -0.45
    iastes
    -0.44
    NavItem
    -0.44
    NamedQueries
    -0.44
    expandindo
    -0.44
    POSITIVE LOGITS
     Saxon
    0.54
    owulf
    0.52
    Saxon
    0.49
     Beowulf
    0.48
     Viking
    0.47
    Viking
    0.46
     Anglo
    0.46
    Anglo
    0.44
     viking
    0.42
    
    0.41
    Activations Density 0.451%

    No Known Activations