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. 1-GEMMASCOPE-RES-16K
    6. 7283
    Prev
    Next
    INDEX
    Explanations

    data type declarations, specifically related to unsigned integers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.51
    科
    -0.51
     bè
    -0.48
    \"\
    -0.47
    ärme
    -0.47
    DAS
    -0.46
     professionali
    -0.46
    SOS
    -0.46
     DAS
    -0.46
     ETC
    -0.46
    POSITIVE LOGITS
    uint
    4.15
     uint
    3.89
    Uint
    1.59
    UINT
    1.56
    UInt
    1.52
     UInt
    1.45
     UINT
    1.41
    stdint
    1.36
    ushort
    1.31
     ushort
    1.20
    Activations Density 0.121%

    No Known Activations