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-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52970
    Prev
    Next
    INDEX
    Explanations

    elements of imaginative play and storytelling

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

    applications, student reflection, pro status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Espèce
    -0.55
    Demografía
    -0.48
     giant
    -0.47
    UrlResolution
    -0.47
    Begriffsklä
    -0.46
     WebDriverWait
    -0.44
    CurrentValue
    -0.44
     brachte
    -0.43
    imanapun
    -0.43
    ஈ
    -0.42
    POSITIVE LOGITS
     invokingState
    0.70
    tagHelperRunner
    0.65
    saraba
    0.64
     EconPapers
    0.63
     dAtA
    0.61
    ruled
    0.59
    RegistryLite
    0.58
     Officially
    0.57
     Ears
    0.57
     official
    0.56
    Activations Density 0.129%

    No Known Activations