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. 122887
    Prev
    Next
    INDEX
    Explanations

    keywords related to database creation and management

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

    Technical terms and code fragments in scientific papers, programming documentation, and mathematical notation, often representing variable names, functions, or specialized terminology.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     '\\;'
    -0.58
     ujednoznacz
    -0.57
    ariConfig
    -0.49
    ">//
    -0.48
    AndEndTag
    -0.48
     enfans
    -0.48
     espir
    -0.47
    nasse
    -0.46
    Geplaatst
    -0.46
     ordinaires
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.42
    つ
    0.39
     صوتيه
    0.37
    AccessorTable
    0.36
    DeleteBehavior
    0.35
    取
    0.34
     Gw
    0.31
     esternos
    0.31
     拼
    0.31
    aventure
    0.31
    Activations Density 0.060%

    No Known Activations