© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4293
    Prev
    Next
    INDEX
    Explanations

    json formatted data structures and their elements

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

    Code or brackets following a keyword

    np_acts-logits-general · gemini-2.0-flash

    gringo Star

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.63
     MessageBoxIcon
    -0.60
    tableFuture
    -0.58
     المعيارى
    -0.58
     चीज़ों
    -0.57
     HasFactory
    -0.57
    Portail
    -0.56
    YourGuide
    -0.54
    iffion
    -0.53
    Rüyada
    -0.53
    POSITIVE LOGITS
    évaluateur
    0.36
     Grüsse
    0.35
     Daher
    0.31
    XmlAccessType
    0.30
    tagHelper
    0.30
     Flucht
    0.30
     Wex
    0.30
     jó
    0.29
    ParallelGroup
    0.29
    NotEqualTo
    0.29
    Activations Density 2.581%

    No Known Activations