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. 51831
    Prev
    Next
    INDEX
    Explanations

    technical specifications and components of electronic devices

    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
     AssemblyCulture
    -0.51
    intios
    -0.49
    httphttps
    -0.47
    ⤹
    -0.47
    🧹
    -0.46
    PostExecute
    -0.46
    
    -0.46
    PreExecute
    -0.46
    rungsseite
    -0.46
    Aholisi
    -0.45
    POSITIVE LOGITS
     replaceable
    0.38
    見えない
    0.36
    ValueStyle
    0.35
    JOptionPane
    0.34
     составля
    0.32
     quality
    0.31
    jspx
    0.31
    infect
    0.31
     upgrade
    0.30
    addWidget
    0.30
    Activations Density 0.061%

    No Known Activations