© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11402
    Prev
    Next
    INDEX
    Explanations

    phrases indicating extreme experiences or superlative statements

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

    "ever" followed by a past participle

    np_acts-logits-general · gemini-2.0-flash

    ever known/seen/done/met/saw

    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
     indígen
    -0.86
     queſta
    -0.85
    writeFieldEnd
    -0.84
    ロウィン
    -0.83
     témoig
    -0.81
    principalColumn
    -0.80
     estadounid
    -0.79
     myſelf
    -0.79
     increí
    -0.79
    parsedMessage
    -0.78
    POSITIVE LOGITS
     EVER
    0.55
    Ever
    0.54
     Ever
    0.54
     ever
    0.52
     jemals
    0.49
    ever
    0.49
    .
    0.46
    ,
    0.44
     person
    0.43
    EVER
    0.39
    Activations Density 0.117%

    No Known Activations