© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5457
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss specific scientific or statistical methodologies and their evaluations

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

    "in terms of"

    np_acts-logits-general · gemini-2.0-flash

    expressed in terms of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mobileqq
    -0.58
    انجليز
    -0.55
    новниш
    -0.49
    出版年
    -0.49
    rawDesc
    -0.47
    ContentAsync
    -0.47
     Winaray
    -0.47
    wikidata
    -0.47
    VIAF
    -0.47
     blazer
    -0.45
    POSITIVE LOGITS
     utilized
    0.43
     utilised
    0.41
     undertaken
    0.40
     properly
    0.40
     correctamente
    0.39
     devait
    0.39
     edil
    0.38
     correctly
    0.38
    され
    0.38
     chosen
    0.38
    Activations Density 2.721%

    No Known Activations