© 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. 9329
    Prev
    Next
    INDEX
    Explanations

    references to specific terms or phrases associated with a particular group or community, particularly those linked to the term "Bas."

    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
    eynman
    -0.46
    pung
    -0.40
    ArrowToggle
    -0.39
    eryn
    -0.39
    enumi
    -0.38
     Ucraina
    -0.38
     Mov
    -0.38
    xnn
    -0.37
    шення
    -0.37
    zeiro
    -0.36
    POSITIVE LOGITS
     Bas
    3.44
     bas
    3.44
    Bas
    3.33
    bas
    2.94
     BAS
    2.75
    BAS
    2.48
     basal
    2.25
     Basal
    2.22
     Bass
    2.20
     Bassett
    2.16
    Activations Density 0.906%

    No Known Activations