© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 50768
    Prev
    Next
    INDEX
    Explanations

    phrases involving questions and answers

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

    strong language

    np_acts-logits-general · gemini-2.5-flash-lite

    discourse scaffolding and emphasis markers in informal text—negations, conjunctions, pronouns, quoted Q&A, repetitions, and list/quantity phrasing that signal conversational tone and intensity.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     recognized
    -0.37
     recognised
    -0.35
     sejumlah
    -0.33
    griffe
    -0.32
     voeten
    -0.32
     ristor
    -0.30
     sava
    -0.30
     ancha
    -0.29
     spirituale
    -0.29
     reconocido
    -0.29
    POSITIVE LOGITS
    GEBURTSDATUM
    0.79
     oprot
    0.75
    rungsseite
    0.71
     betweenstory
    0.71
     autorytatywna
    0.69
    fuck
    0.68
    IntoConstraints
    0.67
    fucking
    0.67
     goddamn
    0.67
     fuckin
    0.66
    Activations Density 0.121%

    No Known Activations