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. 9898
    Prev
    Next
    INDEX
    Explanations

    Java methods that convert strings into numerical values

    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
     nullptr
    -0.71
     <<<<<<<<<<<<<<
    -0.58
     nil
    -0.57
    чей
    -0.55
     éto
    -0.52
    omburg
    -0.52
    raire
    -0.52
    czaj
    -0.51
    وروب
    -0.51
    __);
    -0.51
    POSITIVE LOGITS
    parseInt
    1.87
    parseLong
    1.60
    parseDouble
    1.54
     parseInt
    1.50
    parseFloat
    1.13
     parseFloat
    1.02
    strconv
    0.92
     AssemblyVersion
    0.78
    URLException
    0.74
     StringTokenizer
    0.72
    Activations Density 0.032%

    No Known Activations