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. 10-GEMMASCOPE-RES-16K
    6. 3000
    Prev
    Next
    INDEX
    Explanations

    references to individuals and organizations in leadership or ownership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.95
     noDo
    -0.85
    كويكب
    -0.79
    MLLoader
    -0.76
    elemField
    -0.75
     createSlice
    -0.75
     Walkover
    -0.74
    tanleria
    -0.73
     estimés
    -0.71
     Réponses
    -0.71
    POSITIVE LOGITS
    AddHtmlAttribute
    0.52
    tagext
    0.50
     cui
    0.44
     for
    0.41
     formerly
    0.40
     originally
    0.39
    rungsseite
    0.38
     ugu
    0.38
    umal
    0.36
    sous
    0.36
    Activations Density 0.415%

    No Known Activations