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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 2313
    Prev
    Next
    INDEX
    Explanations

    terms related to legal exemptions and financial discounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.53
    ViewFeatures
    -0.50
    째
    -0.50
     Roskov
    -0.49
    ubereitung
    -0.48
    aufbau
    -0.46
    谨
    -0.46
    lious
    -0.44
     Bani
    -0.43
     knex
    -0.43
    POSITIVE LOGITS
     discount
    0.96
     concessions
    0.89
     discounts
    0.89
     exemption
    0.84
     conces
    0.80
     waiver
    0.80
     concession
    0.79
     discounted
    0.78
    discount
    0.77
     Discount
    0.76
    Activations Density 0.447%

    No Known Activations