© 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. 2863
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedural or methodological actions

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

    Comes before instructions or explanations

    np_acts-logits-general · gemini-2.0-flash

    to do so

    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
     ModelExpression
    -0.56
    ſelves
    -0.55
    RTDA
    -0.53
    ngdoc
    -0.52
    Personensuche
    -0.52
     plufieurs
    -0.52
    indd
    -0.51
     quæ
    -0.50
    ToBounds
    -0.48
     increí
    -0.48
    POSITIVE LOGITS
     rely
    0.42
     relies
    0.41
     requires
    0.40
     depends
    0.39
     asked
    0.35
     сначала
    0.32
     by
    0.32
     depend
    0.31
    jarse
    0.31
     involves
    0.30
    Activations Density 0.524%

    No Known Activations