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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 283
    Prev
    Next
    INDEX
    Explanations

    instances of seeking or discovering underlying themes and ideals

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

    phrases with words like "you'll find" or "can be found".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    transQ
    -0.60
    RTEE
    -0.43
     متحده
    -0.43
    ManyToOne
    -0.43
    httphttps
    -0.42
    GEBURTSDATUM
    -0.41
     MediatR
    -0.37
     purpoſe
    -0.37
    emlrt
    -0.36
     ✭✭
    -0.35
    POSITIVE LOGITS
     najdete
    0.57
     näky
    0.57
     appearances
    0.56
    WillAppear
    0.54
     voorbij
    0.49
     DbSet
    0.48
     encontrarás
    0.48
     löytyy
    0.47
     ditemui
    0.47
     seen
    0.47
    Activations Density 0.151%

    No Known Activations