© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13359
    Prev
    Next
    INDEX
    Explanations

    instructions for performing specific tasks or procedures

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

    Questions/Instructions and how to answer them

    np_acts-logits-general · gemini-2.0-flash

    finding instructional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     queſta
    -0.72
    parsedMessage
    -0.65
    IntoConstraints
    -0.65
    Tikang
    -0.62
    styleUrls
    -0.59
     pleaſure
    -0.59
    CodedInputStream
    -0.56
     ſch
    -0.54
     Normdatei
    -0.54
     getItemCount
    -0.54
    POSITIVE LOGITS
    Show
    0.44
    Theme
    0.39
     citada
    0.37
    Example
    0.36
    Session
    0.36
     geçir
    0.36
     peristiwa
    0.36
    bantu
    0.36
    Trong
    0.35
     vicenda
    0.34
    Activations Density 0.036%

    No Known Activations