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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 16227
    Prev
    Next
    INDEX
    Explanations

    terms related to multipart data encoding and processing in MIME

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.85
     "..\..\
    -0.79
     propOrder
    -0.71
     Houſe
    -0.70
     houſe
    -0.70
    +#+
    -0.69
     IndexError
    -0.67
     Reſ
    -0.64
    didSet
    -0.63
     "..\..\..\
    -0.63
    POSITIVE LOGITS
    StandardCharsets
    0.73
     MemoryStream
    0.66
    BitmapFactory
    0.65
    ByteArray
    0.60
    readAs
    0.57
    ioutil
    0.56
    getBytes
    0.55
    JScrollPane
    0.55
    NSData
    0.53
    objPHPExcel
    0.51
    Activations Density 0.370%

    No Known Activations