© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3257
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical values and embedded forms in structured data formats

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

    programming-related tokens from various software development languages and frameworks (like .NET, Java, Apache, XML, XAML).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    featureID
    -1.30
    parsedMessage
    -1.18
    tagHelperRunner
    -1.17
    AddTagHelper
    -1.15
    transQ
    -1.13
    principalColumn
    -1.09
     typelib
    -1.08
    Personendaten
    -1.04
    RegressionTest
    -1.03
    SharedDtor
    -1.03
    POSITIVE LOGITS
     
    0.56
    .
    0.56
     a
    0.52
    ↵↵
    0.50
      
    0.49
    ,
    0.47
    ::
    0.45
     the
    0.45
     General
    0.45
    <strong>
    0.44
    Activations Density 0.012%

    No Known Activations