Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 62171
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and colloquial language

    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
    AsUp
    -0.58
    니다
    -0.51
     sẻ
    -0.50
     Deutschlands
    -0.49
     Hotspur
    -0.48
     Martí
    -0.48
     agi
    -0.48
    Più
    -0.47
    elv
    -0.47
    Opal
    -0.46
    POSITIVE LOGITS
     freakin
    0.65
     fuckin
    0.55
     fucking
    0.53
     freaking
    0.52
    arangay
    0.49
    padek
    0.49
     exclamation
    0.49
    erintah
    0.48
     viewDidLoad
    0.48
     biß
    0.48
    Activations Density 0.041%

    No Known Activations