© 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. 6145
    Prev
    Next
    INDEX
    Explanations

    function argument notations in programming code

    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
     Anſ
    -0.62
     juſ
    -0.62
     tranſ
    -0.59
     faſt
    -0.56
     Diſ
    -0.56
     diſt
    -0.55
     abſ
    -0.55
     purpoſe
    -0.54
     Inſ
    -0.54
     Reſ
    -0.54
    POSITIVE LOGITS
     ->
    1.41
     <-
    0.63
    )->
    0.62
    SpringBootTest
    0.57
    >::
    0.55
    Autoritní
    0.53
     -->
    0.49
     <--
    0.47
    /*:
    0.47
     <!--
    0.47
    Activations Density 0.067%

    No Known Activations