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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8099
    Prev
    Next
    INDEX
    Explanations

    chemical substances and their concentrations in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    tvguidetime
    -0.61
    SharedCtor
    -0.59
     queſta
    -0.58
    AsUp
    -0.56
    AndroidJUnit
    -0.56
     NSCoder
    -0.54
    jsii
    -0.54
    BeginContext
    -0.54
    GHIJKLM
    -0.54
     Photocase
    -0.53
    POSITIVE LOGITS
    horabuena
    0.41
     Allerdings
    0.37
    mainen
    0.35
     kaynağından
    0.35
     muerto
    0.35
     terbentuk
    0.33
     éstos
    0.33
    combined
    0.32
     colombiano
    0.32
     StatefulWidget
    0.32
    Activations Density 0.002%

    No Known Activations