© 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. 4012
    Prev
    Next
    INDEX
    Explanations

    details related to technical specifications and capabilities of machinery or equipment

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

    Value or measurement accompanied by a unit

    np_acts-logits-general · gemini-2.0-flash

    quantities and units

    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
     tölt
    -0.26
     fim
    -0.26
    posób
    -0.24
    riebene
    -0.24
     langue
    -0.24
     useEffect
    -0.24
     encar
    -0.23
    anguage
    -0.23
     BaseActivity
    -0.23
     collected
    -0.23
    POSITIVE LOGITS
     ModelExpression
    0.84
     snippetHide
    0.73
     ujednoznacz
    0.65
     ویکی‌پدی
    0.64
     ArrayAdapter
    0.63
    twimg
    0.62
     ब्रेकडाउन
    0.61
    клопе
    0.60
     doInBackground
    0.60
     Normdatei
    0.59
    Activations Density 0.280%

    No Known Activations