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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15254
    Prev
    Next
    INDEX
    Explanations

    references to Scottish identity and politics

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

    Scotland, Scottish, or Scottish contexts

    np_acts-logits-general · gemini-2.0-flash

    Scottish places and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fastjson
    -0.50
    Бахар
    -0.49
    UnknownFields
    -0.46
    jspb
    -0.44
     Autorizaciones
    -0.43
    protoimpl
    -0.43
     Putnam
    -0.42
     jTextField
    -0.42
     Winslow
    -0.41
    toJSONString
    -0.41
    POSITIVE LOGITS
     Scotland
    0.95
     Scottish
    0.94
    Scotland
    0.91
    Scottish
    0.89
     scottish
    0.81
     Glasgow
    0.79
    Glasgow
    0.75
     Scotch
    0.73
     scot
    0.66
     Edinburgh
    0.65
    Activations Density 0.238%

    No Known Activations