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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 53453
    Prev
    Next
    INDEX
    Explanations

    sections and headings in structured documents

    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
    AndEndTag
    -0.81
     AssemblyProduct
    -0.75
    CppCodeGen
    -0.73
    الدراسه
    -0.68
    tonode
    -0.67
    存于互联网档案馆
    -0.65
     فريبيس
    -0.64
     Biôgrafia
    -0.63
    iſchen
    -0.62
    writeField
    -0.61
    POSITIVE LOGITS
    $_['
    0.32
    subsection
    0.31
    subsubsection
    0.30
     principales
    0.29
    ..\..\
    0.27
     主要
    0.27
    Adapun
    0.27
     Lingkungan
    0.27
    ocarpus
    0.26
     the
    0.26
    Activations Density 0.002%

    No Known Activations