© 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. 14344
    Prev
    Next
    INDEX
    Explanations

    elements of programming structures and code documentation

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

    Code, variable, or function definitions

    np_acts-logits-general · gemini-2.0-flash

    code examples

    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
    .*")]
    -0.49
     betweenstory
    -0.48
     jsPsych
    -0.45
     
    -0.44
    LookAnd
    -0.41
     AssemblyCompany
    -0.41
     Fre
    -0.39
    GraphicsUnit
    -0.37
    tamina
    -0.37
    is
    -0.36
    POSITIVE LOGITS
    Manbalar
    0.70
    fjspx
    0.61
     Infór
    0.57
     الرياضيه
    0.57
    haikusbot
    0.56
    isContained
    0.55
    цездатний
    0.53
    তথ্যসূত্র
    0.52
     gyhoeddwyd
    0.52
     ſind
    0.51
    Activations Density 0.333%

    No Known Activations