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. 20-GEMMASCOPE-RES-16K
    6. 1978
    Prev
    Next
    INDEX
    Explanations

    financial transactions and related monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.64
    featureID
    -0.56
    Sharper
    -0.50
    liers
    -0.50
    BagLayout
    -0.48
    adhé
    -0.48
    rån
    -0.47
    ontaneous
    -0.47
    ように
    -0.47
    urnal
    -0.47
    POSITIVE LOGITS
     worth
    2.59
     valued
    2.17
     Worth
    1.90
     WORTH
    1.86
    worth
    1.85
    Worth
    1.80
     value
    1.74
    valued
    1.72
     amounting
    1.71
     totaling
    1.67
    Activations Density 0.255%

    No Known Activations