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

    Neuronpedia

    Jacobian LensNEW
    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. 15335
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity for analytical classification and assessment in complex scenarios

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

    Tokens that often precede coordinating conjunctions or conjunctive adverbs

    np_acts-logits-general · gemini-2.0-flash

    consequences and explanations

    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
    IntentFilter
    -0.28
    ждую
    -0.27
    Jeografia
    -0.27
    ":"+
    -0.26
     acho
    -0.26
    riente
    -0.26
     parques
    -0.26
     Vier
    -0.26
    Referencer
    -0.26
    Читайте
    -0.25
    POSITIVE LOGITS
    CloseOperation
    0.60
     jScrollPane
    0.59
     InputDecoration
    0.57
    outSlope
    0.54
     ब्रेकडाउन
    0.53
     CreateTagHelper
    0.53
     Administrativna
    0.53
    parsedMessage
    0.52
     AssemblyCulture
    0.51
    WindowConstants
    0.50
    Activations Density 0.491%

    No Known Activations