© 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. 1-GEMMASCOPE-RES-16K
    6. 7929
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic or computational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hygiène
    -0.45
     e
    -0.41
     El
    -0.40
    accompagnement
    -0.38
     el
    -0.38
    humidité
    -0.36
    apparence
    -0.36
    appartamento
    -0.36
    extrémité
    -0.35
     em
    -0.34
    POSITIVE LOGITS
    ever
    1.66
    equ
    1.57
    eg
    1.51
    eq
    1.50
    ele
    1.48
    ev
    1.48
    ech
    1.46
    ew
    1.45
    ey
    1.44
    ez
    1.43
    Activations Density 0.373%

    No Known Activations