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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15972
    Prev
    Next
    INDEX
    Explanations

    references to digital technology and its various applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     stmt
    -0.44
     considerations
    -0.42
     considered
    -0.42
    chein
    -0.42
    ouvrage
    -0.40
     expected
    -0.40
    ening
    -0.37
    anın
    -0.36
     Considerations
    -0.36
    stehen
    -0.36
    POSITIVE LOGITS
    Digital
    1.20
     digital
    1.14
     DIGITAL
    1.13
    DIGITAL
    1.13
     Digital
    1.10
    digital
    1.09
     digitally
    0.98
     digitale
    0.96
     Digit
    0.93
    Digitized
    0.87
    Activations Density 0.073%

    No Known Activations