© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 20069
    Prev
    Next
    INDEX
    Explanations

    derogatory language and expressions of frustration or anger

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

    profanity and insults

    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-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
    Personendaten
    -0.56
    UnknownFields
    -0.41
    requent
    -0.40
     cercana
    -0.40
     frequência
    -0.40
    Familiar
    -0.38
     příjem
    -0.38
    wiście
    -0.38
     ویکی‌پدی
    -0.38
     kjent
    -0.38
    POSITIVE LOGITS
     fuckin
    0.91
     shit
    0.91
     fucking
    0.90
    fuck
    0.85
     shitty
    0.84
     bastard
    0.84
     bastards
    0.83
     goddamn
    0.81
     bullshit
    0.81
    Shit
    0.81
    Activations Density 0.052%

    No Known Activations