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. 22-GEMMASCOPE-RES-16K
    6. 10929
    Prev
    Next
    INDEX
    Explanations

    references to places and accessibility

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

    Time or effort related to travel

    np_acts-logits-general · gemini-2.0-flash

    hours and distance

    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
    TagMode
    -0.63
     يتيمه
    -0.61
    اریخ
    -0.53
     surla
    -0.50
    principalTable
    -0.49
    NameInMap
    -0.48
    Captor
    -0.47
    MENAFN
    -0.47
    Clik
    -0.47
    Mediabestanden
    -0.46
    POSITIVE LOGITS
     travel
    1.98
     drive
    1.79
     traveled
    1.72
     travelled
    1.72
     travelling
    1.71
     traveling
    1.71
     commute
    1.67
    travel
    1.67
     Travel
    1.60
     driving
    1.59
    Activations Density 0.226%

    No Known Activations