© 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. 22-GEMMASCOPE-RES-16K
    11. 14460
    Prev
    Next
    INDEX
    Explanations

    programming constructs involving conditional statements and input/output operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.43
     informée
    -0.40
     članak
    -0.36
    المشاركات
    -0.34
     msglen
    -0.34
    processable
    -0.33
     disambiguazione
    -0.30
    NullException
    -0.29
     Discretion
    -0.29
     transfieras
    -0.29
    POSITIVE LOGITS
    awtextra
    0.52
    ViewFeatures
    0.52
     InputDecoration
    0.50
    íncia
    0.48
     kasarigan
    0.48
     GenerationType
    0.46
     vectorielles
    0.45
    CrossRef
    0.44
    ofold
    0.44
     folds
    0.44
    Activations Density 0.392%

    No Known Activations