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. 69
    Prev
    Next
    INDEX
    Explanations

    instances of the word "often."

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

    the word "often" in various contexts.

    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
    IntoConstraints
    -0.56
     Schild
    -0.52
    shiro
    -0.50
    IContainer
    -0.48
     Shiro
    -0.47
    deinit
    -0.46
    PreExecute
    -0.43
     stringBuilder
    -0.41
    瘩
    -0.41
     chaus
    -0.40
    POSITIVE LOGITS
     often
    1.17
    often
    1.10
    Often
    1.09
     Often
    1.06
     frequently
    0.96
     oftentimes
    0.95
    frequently
    0.94
     často
    0.92
     spesso
    0.91
     souvent
    0.89
    Activations Density 0.038%

    No Known Activations