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. 0-GEMMASCOPE-RES-16K
    6. 226
    Prev
    Next
    INDEX
    Explanations

    the keyword "Constants" and related terminology in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lok
    -0.52
    selle
    -0.52
    bed
    -0.51
    pez
    -0.50
     Meyer
    -0.49
     dever
    -0.48
     las
    -0.47
    .
    -0.46
    漏
    -0.46
     suspected
    -0.45
    POSITIVE LOGITS
    Constant
    1.46
    constants
    1.44
    Constants
    1.40
     Constants
    1.36
     constants
    1.35
    Const
    1.32
     Constant
    1.32
     CONST
    1.23
     Const
    1.22
    CONST
    1.21
    Activations Density 0.107%

    No Known Activations