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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80742
    Prev
    Next
    INDEX
    Explanations

    syntax elements and punctuation commonly used in programming code

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     utafitiHapana
    -0.60
     propOrder
    -0.51
    exitRule
    -0.47
     EdgeInsets
    -0.45
     snippetHide
    -0.44
    cshtml
    -0.43
     Mamma
    -0.43
    󠁴
    -0.43
    astéroïdes
    -0.43
     referrerpolicy
    -0.42
    POSITIVE LOGITS
     Biôgrafia
    0.40
    contentLoaded
    0.38
     disponibilités
    0.37
     виправивши
    0.37
    Buenas
    0.36
    Tail
    0.36
     Appreciation
    0.36
    Approval
    0.35
    ofür
    0.35
    енча
    0.35
    Activations Density 0.001%

    No Known Activations