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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5415
    Prev
    Next
    INDEX
    Explanations

    elements related to character traits and development in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getDrawable
    -0.45
    بيرة
    -0.44
     everyone
    -0.41
    CITATION
    -0.41
    έρα
    -0.41
    唆
    -0.41
    ękuję
    -0.40
     réjou
    -0.40
    peche
    -0.39
     herkes
    -0.38
    POSITIVE LOGITS
     protagonist
    0.82
    Diweddarwch
    0.75
     NavController
    0.75
     narrator
    0.73
     فريبيس
    0.73
     propOrder
    0.68
     tartalomajánló
    0.64
    хьтан
    0.63
    BeginContext
    0.63
    énario
    0.62
    Activations Density 0.284%

    No Known Activations