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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 78
    Prev
    Next
    INDEX
    Explanations

    coding-related terms or concepts related to programming structures and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code or programming-related terminology, particularly related to computation and variables.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     judicia
    -0.36
    sweise
    -0.32
     runnable
    -0.30
     definición
    -0.29
    rament
    -0.29
     premium
    -0.29
    SIGINT
    -0.29
     qualitatively
    -0.28
     Anlass
    -0.28
     viscose
    -0.28
    POSITIVE LOGITS
    Enllaces
    0.72
     '\\;'
    0.64
    帖最后由
    0.62
    dafx
    0.61
     AssemblyVersion
    0.59
    Xna
    0.59
    PerformLayout
    0.55
     externi
    0.54
    发表于
    0.53
     imageNamed
    0.52
    Activations Density 0.570%

    No Known Activations