Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 781
    Prev
    Next
    INDEX
    Explanations

    information related to elevations and altitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.67
     AssemblyProduct
    -0.58
    msgSender
    -0.56
     للمعارف
    -0.54
    errHandler
    -0.53
     GetEnumerator
    -0.52
    ymal
    -0.52
    mailto
    -0.52
    fjspx
    -0.51
    Viitteet
    -0.51
    POSITIVE LOGITS
     elevation
    0.84
     altitude
    0.80
     elevations
    0.79
    Altitude
    0.68
     Altitude
    0.64
     Elevation
    0.64
     altitudes
    0.64
    elevation
    0.63
     heights
    0.61
    TagMode
    0.59
    Activations Density 0.080%

    No Known Activations