Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6764
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to powers and subscripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {}",
    -0.55
    öten
    -0.53
     --
    -0.52
    ";
    -0.52
     lượt
    -0.52
     \&
    -0.50
    \":
    -0.50
     autor
    -0.49
    );\
    -0.48
     nemo
    -0.48
    POSITIVE LOGITS
     myſelf
    1.07
     itſelf
    0.99
     ujednoznacz
    0.98
     <<<<<<<<<<<<<<
    0.96
     Houſe
    0.96
     Reſ
    0.94
     himſelf
    0.93
    ſelf
    0.92
     Diſ
    0.91
     Jefus
    0.91
    Activations Density 0.206%

    No Known Activations