© 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. 30-GEMMASCOPE-RES-16K
    11. 10682
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or quantities

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

    Uncommon characters and symbols

    np_acts-logits-general · gemini-2.0-flash

    tech and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    duled
    -0.43
    MIDDLEWARE
    -0.38
    tahui
    -0.35
     Maître
    -0.32
    SizeMode
    -0.32
     Houſe
    -0.31
     updated
    -0.31
     odkazy
    -0.31
     saldır
    -0.30
     Dances
    -0.29
    POSITIVE LOGITS
    uxxxx
    0.96
     Roskov
    0.61
    ScopeManager
    0.60
     Италијани
    0.57
    IUrlHelper
    0.54
    =$?
    0.52
    InjectAttribute
    0.51
    .*")]
    0.51
    aarrggbb
    0.50
    httphttps
    0.48
    Activations Density 0.347%

    No Known Activations