© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12603
    Prev
    Next
    INDEX
    Explanations

    terms related to visa and immigration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
    løs
    -0.41
    ControllerAdvice
    -0.39
     ainfi
    -0.35
     régionale
    -0.35
    écou
    -0.35
    Bronnen
    -0.34
     relatifs
    -0.33
     redé
    -0.33
     Aussch
    -0.32
    NewReader
    -0.32
    POSITIVE LOGITS
     visa
    0.85
     Visa
    0.84
    Visa
    0.79
     visas
    0.75
     Schengen
    0.60
    签证
    0.58
     passport
    0.57
    visa
    0.57
     passports
    0.56
     Vis
    0.56
    Activations Density 0.298%

    No Known Activations