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. 17-GEMMASCOPE-RES-16K
    6. 5843
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tr
    -0.57
    Cách
    -0.53
     
    -0.53
    pss
    -0.51
     tr
    -0.51
     cre
    -0.51
    菁
    -0.50
    ↵
    -0.49
     V
    -0.49
     (
    -0.48
    POSITIVE LOGITS
     myſelf
    1.03
     himſelf
    1.01
     itſelf
    0.94
     themſelves
    0.94
     Monfieur
    0.93
     raiſ
    0.93
    Datuak
    0.92
     ſeveral
    0.91
     Jefus
    0.90
     ―――――
    0.90
    Activations Density 0.667%

    No Known Activations