© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 14678
    Prev
    Next
    INDEX
    Explanations

    concepts related to evaluating importance or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consultato
    -0.64
    olari
    -0.59
    urrent
    -0.58
    TabIndex
    -0.57
    nocześnie
    -0.57
    DECREF
    -0.57
    ensively
    -0.57
    findpost
    -0.57
    Carrière
    -0.56
     насељу
    -0.55
    POSITIVE LOGITS
     handlar
    0.73
     kıs
    0.59
     subjective
    0.57
    ={({
    0.57
    Ultimately
    0.57
    ਔ
    0.57
     how
    0.56
    AndroidJUnit
    0.56
     matter
    0.56
    addOn
    0.55
    Activations Density 0.265%

    No Known Activations