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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 112146
    Prev
    Next
    INDEX
    Explanations

    technical terms and key concepts related to scientific research and analysis

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

    section titles

    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
    AddTagHelper
    -0.98
    OGND
    -0.93
     يتيمه
    -0.91
     للمعارف
    -0.89
    rungsseite
    -0.87
     utafitiHapana
    -0.87
     وتسجيلات
    -0.82
    niſſe
    -0.81
    iſen
    -0.80
     незавершена
    -0.79
    POSITIVE LOGITS
    </h2>
    0.38
     was
    0.34
     marked
    0.33
     is
    0.31
     '
    0.29
    税込
    0.29
     per
    0.29
     \\
    0.28
     defined
    0.28
    <eos>
    0.28
    Activations Density 0.016%

    No Known Activations