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. 3-GEMMASCOPE-RES-16K
    6. 8300
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getMenuInflater
    -0.69
    EDEFAULT
    -0.64
     šķ
    -0.63
     Hod
    -0.63
     onCancelled
    -0.61
     Leclerc
    -0.60
    BCF
    -0.59
     Rasmus
    -0.59
    (||
    -0.59
    stech
    -0.59
    POSITIVE LOGITS
     pay
    3.13
    pay
    2.85
     Pay
    2.83
     PAY
    2.80
    Pay
    2.78
     pays
    2.67
     paying
    2.62
    PAY
    2.58
     Paying
    2.52
    Paying
    2.38
    Activations Density 0.052%

    No Known Activations