© 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. 12692
    Prev
    Next
    INDEX
    Explanations

    phrases indicating excessive qualities or conditions

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

    Preceding "short," "young," "late," "clever," "tall," or "strong"

    np_acts-logits-general · gemini-2.0-flash

    too adjective/adverb

    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
    شنبه
    -0.52
     HCL
    -0.49
    SourceChecksum
    -0.48
     nhật
    -0.48
     recherchez
    -0.45
    LLocation
    -0.44
    ")]
    -0.43
     calciatore
    -0.43
    mtext
    -0.42
    ]$}
    -0.41
    POSITIVE LOGITS
    too
    1.16
     too
    1.06
    Too
    1.05
     Too
    1.00
     TOO
    0.96
    TOO
    0.90
    oo
    0.66
    toos
    0.65
     Kee
    0.63
    noo
    0.63
    Activations Density 0.058%

    No Known Activations