© 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
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 564
    Prev
    Next
    INDEX
    Explanations

    references to travel guides specifically related to San Francisco

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

    travel guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.52
    principalColumn
    -0.48
    AutoScaleMode
    -0.47
    ttemberg
    -0.44
    AlterField
    -0.43
    archiviato
    -0.43
     HasFactory
    -0.42
    abestanden
    -0.41
    الدراسه
    -0.40
     ModelRenderer
    -0.40
    POSITIVE LOGITS
     tourist
    0.92
     travel
    0.91
     tourists
    0.87
     Tourist
    0.82
     turist
    0.79
     tourism
    0.78
    tourist
    0.75
     Travel
    0.74
     itineraries
    0.73
    Tourist
    0.73
    Activations Density 0.058%

    No Known Activations