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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29762
    Prev
    Next
    INDEX
    Explanations

    terms related to consumer protection legislation and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    consumer protection acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     ExecuteAsync
    -0.49
     drying
    -0.36
    حياتها
    -0.35
    bootstrapcdn
    -0.33
    llingwood
    -0.32
     kiv
    -0.31
    thesis
    -0.30
     sija
    -0.29
    seamnă
    -0.29
     folha
    -0.28
    POSITIVE LOGITS
     consumer
    1.03
     Consumer
    0.96
    consumer
    0.93
     consumers
    0.93
     Consumers
    0.93
    Consumer
    0.89
     CONSUMER
    0.89
    consumers
    0.84
     consumidor
    0.83
    Consumers
    0.82
    Activations Density 0.028%

    No Known Activations