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. 2-GEMMASCOPE-RES-16K
    6. 1129
    Prev
    Next
    INDEX
    Explanations

    references to offers and proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gustav
    -0.64
    ientí
    -0.62
    wachen
    -0.61
    quirrel
    -0.59
    Gustav
    -0.57
     Его
    -0.56
    әне
    -0.55
    stateMutability
    -0.54
    uously
    -0.53
    ancienne
    -0.52
    POSITIVE LOGITS
     offer
    3.50
     Offer
    3.46
    Offer
    3.27
     OFFER
    3.16
    offer
    3.11
     Offers
    2.94
     offers
    2.90
    offers
    2.85
    OFFER
    2.77
    Offers
    2.72
    Activations Density 0.045%

    No Known Activations