© 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 EvalsExportsinterp-engineNEWAPI 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. 11971
    Prev
    Next
    INDEX
    Explanations

    programming functions and their associated parameters or return values

    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
    expandindo
    -0.42
    RegressionTest
    -0.41
    期刊论文
    -0.38
     finally
    -0.38
     finalmente
    -0.37
    UnusedPrivate
    -0.36
    astéro
    -0.36
    RegistryLite
    -0.33
    BufferException
    -0.33
    finally
    -0.33
    POSITIVE LOGITS
     дописавши
    0.57
    ьаж
    0.53
     Assignee
    0.50
    leſs
    0.50
    Viitteet
    0.48
    ndata
    0.48
     uſed
    0.47
    iors
    0.46
     Searle
    0.45
    matum
    0.44
    Activations Density 1.935%

    No Known Activations