© 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. 39-GEMMASCOPE-RES-16K
    6. 1754
    Prev
    Next
    INDEX
    Explanations

    mentions of people named Andrew

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.65
     Wikimedijinoj
    -0.65
     estekak
    -0.65
    expandindo
    -0.61
    RegressionTest
    -0.59
    oa̍t
    -0.59
    yelitis
    -0.58
    <pad>
    -0.57
    thâu
    -0.57
    <unused71>
    -0.57
    POSITIVE LOGITS
    แน่น
    0.30
     práctico
    0.29
     Warhol
    0.28
     Einladung
    0.27
    ๆ
    0.26
    OptionsMenu
    0.26
    ambilan
    0.26
     studio
    0.26
     femininas
    0.26
    halve
    0.25
    Activations Density 0.253%

    No Known Activations