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. 7-GEMMASCOPE-RES-16K
    6. 9225
    Prev
    Next
    INDEX
    Explanations

    references to historical regions and political entities in Europe, particularly those involving Denmark, Schleswig, and Holstein

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.69
     București
    -0.62
     pleaſure
    -0.56
     Brasília
    -0.56
     dessus
    -0.54
    ElementException
    -0.54
     Bucure
    -0.53
     nélk
    -0.53
    Extinguishing
    -0.52
    RefreshLayout
    -0.50
    POSITIVE LOGITS
     cref
    0.71
     viewDidLoad
    0.61
    Xna
    0.60
     चीज़ों
    0.59
    TagHelper
    0.58
    orszá
    0.54
    XtraEditors
    0.54
    menor
    0.53
     resourceCulture
    0.52
     '\\;'
    0.52
    Activations Density 0.363%

    No Known Activations