© 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. 11926
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming language syntax

    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
    bekistan
    -0.45
     Donut
    -0.42
     maxim
    -0.42
     Inhibition
    -0.40
     donut
    -0.39
     oven
    -0.39
    PointSize
    -0.39
    nextDouble
    -0.38
     Maximal
    -0.38
     Esti
    -0.37
    POSITIVE LOGITS
    RuleContext
    0.59
    RegressionTest
    0.57
     intptr
    0.53
    лтемелер
    0.53
    AndEndTag
    0.52
     iprot
    0.48
    Personendaten
    0.47
    EndProject
    0.46
    ьаж
    0.45
    Chham
    0.44
    Activations Density 0.287%

    No Known Activations