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. 18-GEMMASCOPE-RES-16K
    6. 10227
    Prev
    Next
    INDEX
    Explanations

    statements about societal issues or political actions related to LGBTQ+ matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.86
     surla
    -0.79
     Dulles
    -0.70
    AddTagHelper
    -0.68
    posables
    -0.68
    bootstrapcdn
    -0.68
    Tikang
    -0.63
     الرياضيه
    -0.63
     Pegasus
    -0.62
     Etrus
    -0.62
    POSITIVE LOGITS
     Brooklyn
    0.60
     Park
    0.53
    â
    0.51
    hipster
    0.50
     Bezirks
    0.49
     neighborhood
    0.49
    ContentAsync
    0.48
    hood
    0.48
     gent
    0.47
    HOOD
    0.47
    Activations Density 0.121%

    No Known Activations