Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 85565
    Prev
    Next
    INDEX
    Explanations

    sequences and patterns in mathematical notation

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

    sequences of repetitions, continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    IContainer
    -0.86
    transQ
    -0.69
    KommentareTeilen
    -0.65
    IonicModule
    -0.64
     gustaMe
    -0.61
    TableAdapter
    -0.60
     BrowserModule
    -0.59
    getOutputStream
    -0.59
     fashiola
    -0.58
     zwiſchen
    -0.58
    POSITIVE LOGITS
    cdots
    0.49
    ...
    0.42
     ...
    0.41
    ddots
    0.40
     jusqu
    0.36
    PerformLayout
    0.36
     hasta
    0.35
    直到
    0.33
    ldots
    0.33
    ,...,
    0.32
    Activations Density 0.049%

    No Known Activations