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. 864
    Prev
    Next
    INDEX
    Explanations

    information related to streaming services and media availability

    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
    UnusedPrivate
    -0.66
     betweenstory
    -0.64
    Välislingid
    -0.62
    abilia
    -0.58
     IRC
    -0.56
     Toner
    -0.56
    antası
    -0.56
    liseum
    -0.55
     насељу
    -0.55
    oplasty
    -0.55
    POSITIVE LOGITS
     streaming
    1.49
     Netflix
    1.32
     Streaming
    1.22
    Netflix
    1.11
    Streaming
    1.11
     streamed
    1.08
    streaming
    1.07
     stream
    1.05
     streamer
    1.05
     binge
    1.02
    Activations Density 0.106%

    No Known Activations