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. 25-GEMMASCOPE-RES-16K
    6. 7137
    Prev
    Next
    INDEX
    Explanations

    information related to journeys and travel distances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.70
     marchandises
    -0.66
    tonode
    -0.63
     اطلع
    -0.61
     dieux
    -0.61
     réal
    -0.59
    HasForeignKey
    -0.58
     agrí
    -0.57
    enterOuterAlt
    -0.57
     réunis
    -0.55
    POSITIVE LOGITS
     trips
    1.25
     visits
    1.13
     runs
    1.00
     outings
    0.95
     sessions
    0.93
     journeys
    0.93
     rides
    0.91
     excursions
    0.87
     voyages
    0.86
     swims
    0.86
    Activations Density 0.870%

    No Known Activations