© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5627
    Prev
    Next
    INDEX
    Explanations

    descriptions of scenic views and elevated locations

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

    "views" or seeing something from a high place

    np_acts-logits-general · gemini-2.0-flash

    views and overlooks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sumpay
    -0.43
     Wiktionnaire
    -0.38
     Lane
    -0.33
     것이다
    -0.33
     DIR
    -0.33
    Przypisy
    -0.33
     kem
    -0.32
    rasında
    -0.32
     wet
    -0.31
     Sli
    -0.31
    POSITIVE LOGITS
     overlooking
    0.81
     panoramic
    0.79
     vantage
    0.75
    眺望
    0.70
     balcony
    0.69
     lookout
    0.69
     VIEWS
    0.68
     views
    0.68
     overlooks
    0.66
     Views
    0.64
    Activations Density 0.139%

    No Known Activations