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. 15935
    Prev
    Next
    INDEX
    Explanations

    links and references within a document, particularly using HTML anchor tags and related syntax

    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
     nakalista
    -0.82
    IntoConstraints
    -0.59
     насељу
    -0.59
    참고
    -0.58
    jsxFileName
    -0.56
    ྻ
    -0.55
    
    -0.55
    MENAFN
    -0.54
    uxxxx
    -0.54
     deſſen
    -0.53
    POSITIVE LOGITS
    GetKeyDown
    0.36
    getColumnIndex
    0.32
    PerformLayout
    0.30
     DBNull
    0.30
    DBNull
    0.30
     Wicidata
    0.29
    tagext
    0.27
     hinzu
    0.27
    वान
    0.26
     Forumite
    0.26
    Activations Density 1.584%

    No Known Activations