Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 6569
    Prev
    Next
    INDEX
    Explanations

    the start of a new document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    <eos>
    -0.62
     through
    -0.54
    ↵
    -0.51
     that
    -0.49
     
    -0.49
     (
    -0.48
     -
    -0.46
     i
    -0.45
     which
    -0.45
    ,
    -0.44
    POSITIVE LOGITS
     تانيه
    1.17
    ſelf
    1.14
    ſelves
    1.14
     Efq
    1.11
     Мексичка
    1.10
     MainAxisSize
    1.05
     $_"
    1.05
     متعلقه
    1.04
     GenerationType
    1.04
     TextInputType
    1.04
    Activations Density 0.018%

    No Known Activations