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. 19-GEMMASCOPE-RES-16K
    6. 15791
    Prev
    Next
    INDEX
    Explanations

    requests for help or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    شوف
    -0.51
     BoxDecoration
    -0.50
     pinulongan
    -0.49
    ostro
    -0.47
    intrag
    -0.46
    OPHY
    -0.46
    celot
    -0.46
     сайті
    -0.46
    θεν
    -0.45
    sstil
    -0.44
    POSITIVE LOGITS
     thank
    3.68
     Thank
    3.31
     thanks
    3.29
    Thank
    3.21
    thank
    3.11
     THANK
    3.01
     Thanks
    2.99
    thanks
    2.95
     THANKS
    2.93
    Thanks
    2.91
    Activations Density 0.484%

    No Known Activations