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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 7883
    Prev
    Next
    INDEX
    Explanations

    the frequency and occurrence of the word "often."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.84
     Dres
    -0.68
    hydrogenase
    -0.62
    zura
    -0.62
    DataBinding
    -0.61
    Solución
    -0.61
     plads
    -0.61
    getContentPane
    -0.60
     zima
    -0.60
    Спољашње
    -0.60
    POSITIVE LOGITS
     often
    1.31
     Often
    1.25
    Often
    1.21
    often
    1.20
     times
    1.09
     oftentimes
    1.08
    times
    0.99
     menudo
    0.99
     frequently
    0.93
    Frequently
    0.92
    Activations Density 0.079%

    No Known Activations