© 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. 21-GEMMASCOPE-RES-16K
    11. 13098
    Prev
    Next
    INDEX
    Explanations

    expressions related to explanations or detailed descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.35
    JspWriter
    -0.35
     {},
    -0.34
    ########.
    -0.33
     esposo
    -0.33
    writerow
    -0.33
     dragón
    -0.32
     héroe
    -0.31
     término
    -0.30
     piele
    -0.29
    POSITIVE LOGITS
    findpost
    0.69
    ValueGeneration
    0.57
    iffance
    0.54
    asteroide
    0.54
     NSCoder
    0.51
     FetchType
    0.51
    rawDesc
    0.51
    
    0.51
    didSet
    0.50
    AnchorStyles
    0.49
    Activations Density 1.846%

    No Known Activations