© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5573
    Prev
    Next
    INDEX
    Explanations

    references to specific transportation systems or locations

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

    before railway/subway related terms

    np_acts-logits-general · gemini-2.0-flash

    transportation stations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Esau
    -0.56
     Trucking
    -0.53
    帖最后由
    -0.52
     Spisak
    -0.51
     carretera
    -0.51
     Road
    -0.51
     ROAD
    -0.51
    Road
    -0.51
     insurers
    -0.50
    atrician
    -0.49
    POSITIVE LOGITS
     station
    1.09
     stations
    1.08
     subway
    1.06
     Metro
    0.95
     metro
    0.93
     underground
    0.92
     Station
    0.91
     trains
    0.90
     train
    0.88
     Tube
    0.88
    Activations Density 0.159%

    No Known Activations