© 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. 11299
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and variables within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    WithIOException
    -0.76
    featureID
    -0.63
    存于互联网档案馆
    -0.57
     يتيمه
    -0.55
    StoryboardSegue
    -0.55
     estekak
    -0.54
    FieldBuilder
    -0.54
    Personensuche
    -0.53
     nonUne
    -0.52
    UpdateCommand
    -0.52
    POSITIVE LOGITS
    setContentView
    0.46
     sumber
    0.39
     MonoBehaviour
    0.39
    Decimals
    0.39
    yelidikan
    0.38
    Референце
    0.37
    RTSN
    0.36
     sources
    0.36
    openqa
    0.35
     participantes
    0.35
    Activations Density 0.696%

    No Known Activations