© 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. 3-GEMMASCOPE-RES-16K
    6. 8340
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "return to text" or similar navigation commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.54
     Roskov
    -0.51
     estekak
    -0.50
    transQ
    -0.46
     disambiguazione
    -0.44
     Roja
    -0.44
     ſch
    -0.44
    Swag
    -0.43
     zeitung
    -0.43
     ſche
    -0.42
    POSITIVE LOGITS
    恢复
    0.62
     вернуться
    0.61
    回到
    0.60
    恢復
    0.59
     resumed
    0.59
     kembali
    0.58
     wró
    0.57
     resuming
    0.57
     tornare
    0.55
     restored
    0.54
    Activations Density 0.114%

    No Known Activations