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. 17-GEMMASCOPE-RES-16K
    6. 946
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arrived" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ello
    -0.64
     "
    -0.55
    setString
    -0.54
     it
    -0.53
     #
    -0.51
     déb
    -0.51
     phận
    -0.51
      (
    -0.51
     Ros
    -0.50
    getString
    -0.50
    POSITIVE LOGITS
     Arrival
    1.15
     Arrive
    1.12
     arrives
    1.11
     arrivals
    1.09
    arrived
    1.07
     Arri
    1.05
     Theſe
    1.04
    Arri
    1.04
     arrive
    1.03
    Arrive
    1.03
    Activations Density 0.056%

    No Known Activations