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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15559
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to legal actions and statements from officials

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

    preceding days of the week

    np_acts-logits-general · gemini-2.0-flash

    reporting days of the week

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.65
    Sucesor
    -0.57
     EconPapers
    -0.56
     Vikipedi
    -0.48
    EndGlobalSection
    -0.47
    ագրություններ
    -0.47
    adaptiveStyles
    -0.47
    ptonshire
    -0.45
    xase
    -0.44
    клопе
    -0.42
    POSITIVE LOGITS
     yesterday
    2.55
     Tuesday
    2.22
     Thursday
    2.19
     Wednesday
    2.19
     Monday
    2.13
    yesterday
    2.06
     Friday
    2.02
     today
    1.95
     ontem
    1.88
     Saturday
    1.88
    Activations Density 0.345%

    No Known Activations