© 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. 13150
    Prev
    Next
    INDEX
    Explanations

    present tense verbs and contractions

    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
     varandra
    -0.60
     pingente
    -0.59
     början
    -0.58
    CodeDom
    -0.57
     defaultstate
    -0.56
     areia
    -0.52
     varför
    -0.51
     okuyayım
    -0.51
     BrowserModule
    -0.51
     volontà
    -0.51
    POSITIVE LOGITS
    s
    0.66
     outta
    0.65
     اون
    0.59
     gonna
    0.58
     theyre
    0.55
    ll
    0.52
     gotta
    0.52
     GONNA
    0.49
    theres
    0.47
    gotta
    0.46
    Activations Density 0.210%

    No Known Activations