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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10610
    Prev
    Next
    INDEX
    Explanations

    references to economic factors and rising prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.91
     ProtoMessage
    -0.91
    rungsseite
    -0.85
     &___
    -0.74
    ніципалі
    -0.73
    AsUp
    -0.72
     autorytatywna
    -0.71
    -------
    -0.71
    الحياه
    -0.69
    UIControlState
    -0.69
    POSITIVE LOGITS
     prices
    1.65
     price
    1.43
     Prices
    1.35
    Prices
    1.32
    prices
    1.27
     cost
    1.20
     inflation
    1.19
     pricing
    1.15
    price
    1.11
     PRICES
    1.10
    Activations Density 0.169%

    No Known Activations