© 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. 11102
    Prev
    Next
    INDEX
    Explanations

    chemical processes and methodologies related to purification and synthesis

    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
    Abitanti
    -0.35
    ormais
    -0.35
    ---|
    -0.30
     intérieure
    -0.30
    Captor
    -0.29
     menú
    -0.29
     speaking
    -0.29
     movi
    -0.29
     comprend
    -0.28
     insiders
    -0.28
    POSITIVE LOGITS
    offsetof
    0.57
     Administrativna
    0.55
     surla
    0.52
    يميديا
    0.50
    SharedCtor
    0.49
     betweenstory
    0.48
    featureID
    0.48
     InputDecoration
    0.47
    ChildScrollView
    0.46
    şört
    0.46
    Activations Density 0.582%

    No Known Activations