© 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. 13307
    Prev
    Next
    INDEX
    Explanations

    certain elements of structured data, specifically identifiers and context tags

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

    Code snippets with hexadecimal values

    np_acts-logits-general · gemini-2.0-flash

    file path and type codes

    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
     Italijani
    -0.63
     Italijanski
    -0.55
    Personendaten
    -0.54
    تفصیلات
    -0.54
    BufferException
    -0.53
    Aholisi
    -0.49
    kháu
    -0.48
    MessageOf
    -0.48
    Jeografia
    -0.47
     Photocase
    -0.45
    POSITIVE LOGITS
     [*]
    0.58
    
    0.58
     file
    0.58
     filepath
    0.54
    FileType
    0.52
    filepath
    0.50
    uxxxx
    0.50
     filename
    0.50
    file
    0.49
    FilePath
    0.47
    Activations Density 0.372%

    No Known Activations