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. 31-GEMMASCOPE-RES-16K
    6. 16277
    Prev
    Next
    INDEX
    Explanations

    instances of React component lifecycle methods and state management

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

    Code and programming syntax

    np_acts-logits-general · gemini-2.0-flash

    checking code and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🥹
    -0.39
    🫶
    -0.39
     TikTok
    -0.37
    EnableWeb
    -0.37
    🥲
    -0.36
    DoubleQuotes
    -0.36
     Omicron
    -0.35
     tiktok
    -0.34
     pandemic
    -0.34
    replaceAll
    -0.34
    POSITIVE LOGITS
    SequentialGroup
    0.98
    Personendaten
    0.82
    webElementXpaths
    0.70
     betweenstory
    0.69
    EndGlobalSection
    0.66
    Gweler
    0.65
    AndEndTag
    0.61
     Biôgrafia
    0.61
    SaveSave
    0.61
    transQ
    0.59
    Activations Density 0.031%

    No Known Activations