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. 10980
    Prev
    Next
    INDEX
    Explanations

    references to elevations and geographical measurements

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

    Elevation or height measurements

    np_acts-logits-general · gemini-2.0-flash

    elevation and altitude measuring units

    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
    fortawesome
    -0.63
     فريبيس
    -0.54
    StructEnd
    -0.54
    CommonModule
    -0.50
     ISNI
    -0.48
    dited
    -0.47
     للمعارف
    -0.47
    fony
    -0.46
     Ward
    -0.46
     tourner
    -0.46
    POSITIVE LOGITS
     elevation
    1.61
     height
    1.38
     altitude
    1.37
     elevations
    1.34
    elevation
    1.23
     Elevation
    1.22
    Elevation
    1.17
     heights
    1.17
     Height
    1.13
     altitudes
    1.12
    Activations Density 0.206%

    No Known Activations