© 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. 9-GEMMASCOPE-RES-131K
    11. 51862
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and expressions related to quantities and evaluations

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

    comparisons and implications

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ,
    -0.36
    ↵↵
    -0.34
     [*]
    -0.33
    <>());
    -0.32
    ✥
    -0.31
    DebuggerNonUser
    -0.31
    Â
    -0.31
      
    -0.31
    CreateModel
    -0.31
    ۥ
    -0.31
    POSITIVE LOGITS
     للمعارف
    0.71
    tanleria
    0.62
     forState
    0.59
    EDEFAULT
    0.56
    Autoritní
    0.56
    OGND
    0.55
     ویکی‌پدی
    0.54
     saites
    0.52
    +#+#
    0.51
    rawDesc
    0.51
    Activations Density 0.152%

    No Known Activations