© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 7755
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to computer programming and software dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     Савезне
    -1.16
     CreateTagHelper
    -1.12
    NameInMap
    -1.09
     bezeichneter
    -1.04
    writeFieldEnd
    -1.03
     transfieras
    -1.00
     betweenstory
    -1.00
    thâu
    -0.99
    SequentialGroup
    -0.95
     للمعارف
    -0.94
    POSITIVE LOGITS
    </strong>
    0.56
    THISDAY
    0.51
    </em>
    0.51
     ordinaires
    0.44
     paille
    0.42
     cotone
    0.41
    </h2>
    0.41
     connues
    0.40
    <unused62>
    0.40
     segítség
    0.40
    Activations Density 0.817%

    No Known Activations