© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2556
    Prev
    Next
    INDEX
    Explanations

    words that indicate conditions or relationships that are definitive or obligatory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Auxiliary verb "was", "are", "have", "were", "can"

    np_acts-logits-general · gemini-2.0-flash

    auxiliary verbs followed by states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PullParser
    -0.64
    tagHelperRunner
    -0.59
     ſon
    -0.55
     pinulongan
    -0.54
    ſelves
    -0.54
     viſ
    -0.53
    RetentionPolicy
    -0.52
    NameInMap
    -0.52
     whoſe
    -0.51
     ſta
    -0.50
    POSITIVE LOGITS
    ParallelGroup
    0.40
    entemente
    0.34
     نکنید
    0.33
     Aqu
    0.33
     also
    0.32
     assuredly
    0.31
     deserve
    0.31
    ädie
    0.31
    Aqu
    0.30
     zitten
    0.30
    Activations Density 0.767%

    No Known Activations