© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2127
    Prev
    Next
    INDEX
    Explanations

    symbols or spacing characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ofrec
    -0.23
     DE
    -0.16
     héro
    -0.16
     surn
    -0.15
     dismin
    -0.15
     uds
    -0.15
     acept
    -0.15
     extend
    -0.14
     fermo
    -0.14
     plancher
    -0.14
    POSITIVE LOGITS
     resourceCulture
    1.03
    NameInMap
    0.90
    fjspx
    0.87
    GEBURTSDATUM
    0.85
    :✨
    0.85
    MigrationBuilder
    0.85
     EconPapers
    0.84
    tvguidetime
    0.84
     autorytatywna
    0.83
     queſta
    0.82
    Activations Density 1.245%

    No Known Activations