© 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. 21-GEMMASCOPE-RES-16K
    11. 13367
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical or statistical equations and results

    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
    WireFormatLite
    -0.47
    Vidite
    -0.45
     ProtoMessage
    -0.42
     beginnetje
    -0.41
    Cyfarwyddwr
    -0.41
     FetchType
    -0.41
    Carriera
    -0.40
    annique
    -0.40
    TemporalType
    -0.38
    ylvan
    -0.38
    POSITIVE LOGITS
    sidemargin
    0.58
    spare
    0.48
    excess
    0.47
     surplus
    0.46
    difference
    0.44
     Margin
    0.44
    Excess
    0.44
     Difference
    0.43
     $[-
    0.43
    parsedMessage
    0.42
    Activations Density 1.421%

    No Known Activations