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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24021
    Prev
    Next
    INDEX
    Explanations

    terms related to seasonal cycles and variations in allele frequencies

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

    annual and seasonal cycles

    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
     Inv
    -0.38
     Master
    -0.36
    Ext
    -0.36
     baby
    -0.35
    Transition
    -0.35
    Inv
    -0.35
     Baby
    -0.35
    abaikan
    -0.34
    DAOImpl
    -0.34
     Übergang
    -0.34
    POSITIVE LOGITS
     yearly
    1.08
     annual
    1.06
    annual
    1.02
     annually
    0.99
    yearly
    0.96
     Yearly
    0.91
    每年
    0.90
    Yearly
    0.88
     anual
    0.86
    毎年
    0.85
    Activations Density 0.113%

    No Known Activations