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. 18-GEMMASCOPE-RES-16K
    6. 10577
    Prev
    Next
    INDEX
    Explanations

    PHP programming constructs and database query operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bufio
    -0.51
     s
    -0.46
     Z
    -0.45
     n
    -0.44
    AnimationsModule
    -0.43
     at
    -0.42
    meni
    -0.42
     er
    -0.41
    zel
    -0.41
    zoni
    -0.41
    POSITIVE LOGITS
    webElementXpaths
    0.78
     Normdatei
    0.77
     disambiguazione
    0.76
    SourceChecksum
    0.73
    AndEndTag
    0.71
    WireFormatLite
    0.70
    VersionUID
    0.69
     NSCoder
    0.67
     varandra
    0.66
     ProtoMessage
    0.66
    Activations Density 0.139%

    No Known Activations