© 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. 4051
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as variables, data types, and method calls

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

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    code delimiters inside programming

    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
     
    -0.41
    acke
    -0.36
     “
    -0.35
    kennt
    -0.35
    vere
    -0.34
    AtIndexPath
    -0.34
    ↵
    -0.34
     Lep
    -0.34
     Mar
    -0.32
     culturally
    -0.32
    POSITIVE LOGITS
     queſta
    0.80
    fromnode
    0.73
    PreferredItem
    0.71
     ſever
    0.68
     ſta
    0.66
     myſelf
    0.65
     referrerpolicy
    0.65
     wikipagina
    0.64
     leſs
    0.64
    WithIOException
    0.63
    Activations Density 1.005%

    No Known Activations