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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122890
    Prev
    Next
    INDEX
    Explanations

    elements and structures related to system or hardware specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    ConstraintMaker
    -0.81
    tagHelperRunner
    -0.80
    aarrggbb
    -0.78
     <<<<<<<<<<<<<<
    -0.77
     disambiguazione
    -0.75
    ArgsConstructor
    -0.75
    <unused52>
    -0.74
    [@BOS@]
    -0.74
    <unused16>
    -0.73
    <unused21>
    -0.73
    POSITIVE LOGITS
    はじめに
    0.32
     forms
    0.25
    devise
    0.24
    áját
    0.23
     fur
    0.23
    master
    0.23
    with
    0.23
     山田
    0.23
    Al
    0.23
    же
    0.23
    Activations Density 0.065%

    No Known Activations