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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9381
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sometimes" and expressions of uncertainty or variability

    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
    er
    -0.68
    ิลปะ
    -0.61
    事は
    -0.60
     Borno
    -0.60
    ing
    -0.59
    gewiesen
    -0.58
    {
    -0.57
    Eliza
    -0.57
    FLAG
    -0.56
    CODES
    -0.56
    POSITIVE LOGITS
    Sometimes
    1.27
     sometimes
    1.26
    sometimes
    1.25
     Sometimes
    1.20
     SOM
    1.14
    SOM
    1.13
     fometimes
    1.03
    adays
    0.97
     oftentimes
    0.96
     manchmal
    0.96
    Activations Density 0.072%

    No Known Activations