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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14674
    Prev
    Next
    INDEX
    Explanations

    references to specific metro or public transport stations

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

    Public transportation: train, metro, or LRT

    np_acts-logits-general · gemini-2.0-flash

    transportation systems and stations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    tvguidetime
    -0.61
     insurer
    -0.56
    帖最后由
    -0.55
    usercontent
    -0.55
     insurers
    -0.53
    +:+
    -0.53
    ="#"
    -0.52
    ISupport
    -0.51
     krę
    -0.50
     Trucking
    -0.49
    POSITIVE LOGITS
     station
    1.27
     stations
    1.19
     Station
    1.05
     subway
    1.04
    station
    0.99
     STATION
    0.98
     underground
    0.98
    Station
    0.96
     Stations
    0.95
     metro
    0.94
    Activations Density 0.153%

    No Known Activations