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. 2984
    Prev
    Next
    INDEX
    Explanations

    references to universities and academic institutions

    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
    }{||
    -0.66
    ick
    -0.62
     krak
    -0.62
    peč
    -0.60
     reak
    -0.59
     Ketch
    -0.58
    бло
    -0.58
     dore
    -0.58
     ocor
    -0.57
     Vierge
    -0.57
    POSITIVE LOGITS
     university
    1.48
     University
    1.43
     universitarios
    1.33
     universities
    1.30
    university
    1.30
    versities
    1.22
    University
    1.22
     Universities
    1.18
    versiti
    1.16
    université
    1.12
    Activations Density 0.046%

    No Known Activations