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. 20-GEMMASCOPE-RES-16K
    6. 15829
    Prev
    Next
    INDEX
    Explanations

    actions and events related to proposals and surprises in relationships

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     abstrait
    -0.47
     plainte
    -0.47
     recueil
    -0.46
     abstrato
    -0.45
    Diweddarwch
    -0.45
     démocratique
    -0.45
     createState
    -0.44
     féminin
    -0.43
     progrès
    -0.42
     fréquent
    -0.42
    POSITIVE LOGITS
     surprise
    0.83
     surprises
    0.67
     Surprise
    0.65
    surprise
    0.63
    Surprise
    0.59
     surprised
    0.59
     snippetHide
    0.57
     sorpresa
    0.54
     wireType
    0.54
    ImageContext
    0.53
    Activations Density 0.139%

    No Known Activations