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. 7-GEMMASCOPE-RES-16K
    6. 15224
    Prev
    Next
    INDEX
    Explanations

    variations of the word "offer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XtraEditors
    -0.81
     Gustav
    -0.79
    Gustav
    -0.69
    quirrel
    -0.69
    HandlerContext
    -0.66
    ientí
    -0.66
    uously
    -0.64
    asin
    -0.63
    alha
    -0.63
    wachen
    -0.62
    POSITIVE LOGITS
     Offers
    1.91
     offers
    1.90
     Offer
    1.87
    offers
    1.84
     offer
    1.82
     OFFER
    1.77
    Offers
    1.76
    Offer
    1.74
     Offering
    1.71
    offer
    1.69
    Activations Density 0.050%

    No Known Activations