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. 20-GEMMASCOPE-RES-16K
    6. 10783
    Prev
    Next
    INDEX
    Explanations

    terms related to coastal geography and tourism activities

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

    beaches, sand, or coastlines

    np_acts-logits-general · gemini-2.0-flash

    beach and sand

    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
    ByExample
    -0.42
     Mark
    -0.40
     ()
    -0.39
      
    -0.39
    koku
    -0.38
    قد
    -0.38
    HasForeignKey
    -0.37
     Mr
    -0.37
     mer
    -0.37
    yscale
    -0.36
    POSITIVE LOGITS
     beaches
    1.44
     sandy
    1.42
     beach
    1.37
     sands
    1.23
    beach
    1.14
     sand
    1.11
     sabbia
    1.08
     beech
    1.08
     BEACH
    1.07
     Beaches
    1.05
    Activations Density 0.047%

    No Known Activations