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. 21-GEMMASCOPE-RES-16K
    6. 7604
    Prev
    Next
    INDEX
    Explanations

    CSS style properties and their values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     location
    -1.15
    Location
    -1.12
     Location
    -1.10
     LOCATION
    -1.02
     locations
    -1.02
     located
    -1.01
     ubicación
    -0.99
    LOCATION
    -0.97
    location
    -0.97
     Locations
    -0.94
    POSITIVE LOGITS
    chier
    0.53
    帖最后由
    0.52
     mergeFrom
    0.51
    ništvo
    0.51
    bigcap
    0.50
    ardino
    0.50
    ẢN
    0.49
    newswire
    0.49
     Fest
    0.49
     архивлан
    0.48
    Activations Density 0.169%

    No Known Activations