© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11088
    Prev
    Next
    INDEX
    Explanations

    complex numerical values and terms related to statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istocene
    -0.38
    iastes
    -0.37
     Cid
    -0.35
    InstrumentedTest
    -0.35
     Administrativna
    -0.34
    onavir
    -0.34
     Monfieur
    -0.34
    mbangkan
    -0.34
    cticide
    -0.33
    Життє
    -0.32
    POSITIVE LOGITS
    aarrggbb
    0.64
    BeginContext
    0.63
    mergeFrom
    0.62
    tagHelperRunner
    0.54
     surla
    0.51
    DockStyle
    0.50
     ExecuteAsync
    0.50
     дописавши
    0.49
    Архівовано
    0.48
    enterOuterAlt
    0.46
    Activations Density 1.261%

    No Known Activations