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. 13271
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue in the text

    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
    BeginContext
    -0.68
    lorette
    -0.57
    ถม
    -0.55
    Външни
    -0.53
    voici
    -0.53
    Минусы
    -0.52
    ystema
    -0.51
    đi
    -0.50
    Folge
    -0.50
    tagHelperRunner
    -0.50
    POSITIVE LOGITS
     teammates
    0.58
    RefNanny
    0.58
    jws
    0.52
    ГЛА
    0.51
     autorytatywna
    0.51
    Sucesor
    0.50
     respekt
    0.50
     focus
    0.49
    bė
    0.48
    espn
    0.47
    Activations Density 0.158%

    No Known Activations