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. 84555
    Prev
    Next
    INDEX
    Explanations

    terms related to the postponement of parenthood and childbearing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Wür
    -0.37
     مت
    -0.35
    itemCount
    -0.34
    toMatchSnapshot
    -0.32
     member
    -0.32
    textwidth
    -0.31
     figure
    -0.31
     Kunt
    -0.31
     apparaître
    -0.31
     Fä
    -0.30
    POSITIVE LOGITS
     postponement
    1.23
     postpone
    1.21
     postponed
    1.15
     postpon
    1.09
     delay
    1.03
     delayed
    1.01
     DELAY
    0.96
     Delay
    0.96
     delaying
    0.93
     Delayed
    0.91
    Activations Density 0.032%

    No Known Activations