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. 8484
    Prev
    Next
    INDEX
    Explanations

    questions marked by the '?' symbol

    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
     Вікі
    -0.60
     saites
    -0.54
    matig
    -0.53
    変わらず
    -0.50
    CodedInputStream
    -0.49
     invokevirtual
    -0.49
    FileChooser
    -0.48
     pack
    -0.47
    SqlDataReader
    -0.47
     Bür
    -0.47
    POSITIVE LOGITS
    ??????
    1.01
    +?
    0.95
    ‍♀️
    0.95
    %?
    0.95
    =?
    0.92
    ’?
    0.92
    ?.
    0.91
    ????????
    0.90
    ‍♂️
    0.90
    ????????????????
    0.85
    Activations Density 0.134%

    No Known Activations