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. 5759
    Prev
    Next
    INDEX
    Explanations

    terms related to egg production and characteristics

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

    egg production and quality

    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
    屓
    -0.58
     فريبيس
    -0.57
     للمعارف
    -0.57
     Clifford
    -0.54
     folyam
    -0.54
     Rainer
    -0.53
    fitrión
    -0.52
    Clifford
    -0.52
    Portale
    -0.52
    нару
    -0.52
    POSITIVE LOGITS
    Egg
    1.29
     Egg
    1.24
     egg
    1.23
    egg
    1.10
     EGG
    1.06
     eggs
    1.05
     Eggs
    1.05
    Eggs
    1.01
    eggs
    0.87
     uovo
    0.85
    Activations Density 0.004%

    No Known Activations