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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103167
    Prev
    Next
    INDEX
    Explanations

    financial details related to costs, discounts, and pricing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     lodge
    -0.46
     idé
    -0.45
     nue
    -0.45
    RTEE
    -0.45
    Dichloropropane
    -0.44
    جمعیت
    -0.44
    hoeddwyd
    -0.42
    amssymb
    -0.42
     eléct
    -0.41
     Lodge
    -0.41
    POSITIVE LOGITS
     paid
    0.48
     payed
    0.45
     bargain
    0.43
     took
    0.41
     plă
    0.41
     price
    0.40
    MSRP
    0.40
     was
    0.40
     cost
    0.40
    имость
    0.39
    Activations Density 0.009%

    No Known Activations