© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 85996
    Prev
    Next
    INDEX
    Explanations

    terms related to tourism

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

    tourist attractions, spots, visas

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Przypisy
    -0.44
    wäh
    -0.44
    ButtonModule
    -0.43
     ExecuteAsync
    -0.43
    Nazwa
    -0.42
     confirmations
    -0.41
     inizio
    -0.41
    myra
    -0.41
    Encourage
    -0.40
     povezave
    -0.40
    POSITIVE LOGITS
     Tourist
    1.04
    tourist
    1.03
     tourist
    0.99
    Tourist
    0.97
     tourists
    0.96
     Tourists
    0.94
     touristes
    0.79
     turist
    0.76
     Touristen
    0.69
     turisti
    0.65
    Activations Density 0.001%

    No Known Activations