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. 3342
    Prev
    Next
    INDEX
    Explanations

    specific references to data formats and organizational structures

    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
     ivelany
    -0.62
    tagHelper
    -0.59
    ziasztok
    -0.52
    IsContent
    -0.51
     hilsen
    -0.47
     disponibilités
    -0.47
    лтемелер
    -0.47
    ſem
    -0.45
    Datuak
    -0.45
    ciclopedia
    -0.44
    POSITIVE LOGITS
    fromnode
    0.49
     betweenstory
    0.46
    ſt
    0.42
    antMatchers
    0.36
    NetworkInfo
    0.36
    期刊论文
    0.35
    TagMode
    0.35
    ppuden
    0.34
     समीक्षक
    0.31
     voies
    0.31
    Activations Density 0.773%

    No Known Activations