© 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. 314
    Prev
    Next
    INDEX
    Explanations

    references to programming tools and software

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

    software or software versions

    np_acts-logits-general · gemini-2.0-flash

    software with version numbers

    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
    writerow
    -0.46
    HostException
    -0.44
     ***!
    -0.44
    archiviato
    -0.42
    antMatchers
    -0.40
    DeleteBehavior
    -0.39
    MigrationBuilder
    -0.39
     ujednoznacz
    -0.38
    WriteLiteral
    -0.38
    MessageInfo
    -0.37
    POSITIVE LOGITS
     software
    0.73
    software
    0.71
    Software
    0.65
     Software
    0.62
     softwares
    0.60
    desktop
    0.59
     SOFTWARE
    0.59
     logiciel
    0.58
    软件
    0.58
    tools
    0.56
    Activations Density 0.393%

    No Known Activations