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. 20-GEMMASCOPE-RES-16K
    6. 3613
    Prev
    Next
    INDEX
    Explanations

    references to geographical elevations and altitudes

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

    Measurements of elevation or altitude

    np_acts-logits-general · gemini-2.0-flash

    elevation and altitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.55
    fortawesome
    -0.49
    INTERVAL
    -0.45
    cokinetics
    -0.45
     ISNI
    -0.45
    licky
    -0.45
    miary
    -0.45
    MaxSize
    -0.44
     Ecke
    -0.43
    Объем
    -0.43
    POSITIVE LOGITS
     elevation
    1.16
     altitude
    1.08
     elevations
    1.00
     altitudes
    0.94
    altitude
    0.88
     level
    0.88
    elevation
    0.85
     niveau
    0.84
    elev
    0.81
     sea
    0.79
    Activations Density 0.134%

    No Known Activations