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. 21-GEMMASCOPE-RES-16K
    6. 8356
    Prev
    Next
    INDEX
    Explanations

    various code concepts and functions related to programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -1.05
    ReusableCell
    -0.90
    audiovisuel
    -0.86
    rrggbb
    -0.81
     الحره
    -0.80
    UnusedPrivate
    -0.77
     ویکی‌پدیای
    -0.77
     pinulongan
    -0.77
     betweenstory
    -0.74
    UserScript
    -0.73
    POSITIVE LOGITS
    fmt
    0.51
    ci
    0.44
    New
    0.42
    ost
    0.41
     yapan
    0.40
    BER
    0.39
     respeto
    0.39
    defer
    0.39
     New
    0.38
     civiles
    0.37
    Activations Density 0.106%

    No Known Activations