© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-GEMMASCOPE-RES-16K
    11. 12514
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cemment
    -0.46
    uelo
    -0.43
     ناد
    -0.42
    antwort
    -0.41
    grunt
    -0.41
     entertainer
    -0.40
     repris
    -0.40
     overlooked
    -0.40
     assailed
    -0.40
    ntax
    -0.39
    POSITIVE LOGITS
     zodat
    0.69
     supaya
    0.65
    Damit
    0.64
    damit
    0.58
     Damit
    0.56
    Чтоб
    0.55
     sodass
    0.52
     чтоб
    0.50
     biar
    0.50
     ensure
    0.50
    Activations Density 0.262%

    No Known Activations