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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12829
    Prev
    Next
    INDEX
    Explanations

    data types and their usage in programming, particularly focusing on byte and buffer representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opsida
    -0.70
    Cher
    -0.58
     Cher
    -0.57
    ďaka
    -0.55
     فہرست
    -0.54
    xFFFFFFFF
    -0.53
    titleMargin
    -0.53
    ləş
    -0.53
    uParam
    -0.51
    છ
    -0.51
    POSITIVE LOGITS
    byte
    3.24
     byte
    2.82
    Byte
    2.08
     Byte
    1.87
     BYTE
    1.68
    BYTE
    1.65
    字节
    0.96
    byt
    0.95
    writeByte
    0.94
    abyte
    0.86
    Activations Density 0.122%

    No Known Activations