© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2432
    Prev
    Next
    INDEX
    Explanations

    conditional structures in programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.68
    __*/
    -0.64
     snippetHide
    -0.62
    quiao
    -0.60
    windowFixed
    -0.60
     ujednoznacz
    -0.58
    <?
    -0.57
     Avic
    -0.56
    >*/
    -0.56
    Clik
    -0.56
    POSITIVE LOGITS
    else
    1.15
     else
    0.95
    Else
    0.74
    elif
    0.72
     Else
    0.70
     ELSE
    0.67
    didSet
    0.60
    ELSE
    0.59
     Otherwise
    0.59
    elseif
    0.57
    Activations Density 0.025%

    No Known Activations