© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4142
    Prev
    Next
    INDEX
    Explanations

    references to tutorials or instructional content

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

    programming and tutorial-related language, especially referring to web development and coding tutorials.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     unieke
    -0.38
     orejas
    -0.38
     berupa
    -0.36
    PageRoute
    -0.35
     flechas
    -0.35
     rantai
    -0.34
     varones
    -0.34
     perdiendo
    -0.34
    ToolStrip
    -0.33
     pelayanan
    -0.33
    POSITIVE LOGITS
     beginner
    0.65
     tutorials
    0.63
     Beginner
    0.61
     simplifié
    0.58
     beginners
    0.58
    fjspx
    0.58
     snippetHide
    0.57
    GOTREF
    0.57
    Beginner
    0.55
     tutorial
    0.55
    Activations Density 0.421%

    No Known Activations