© 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. 10535
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and phrases characterizing appearance or features

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

    Adjectives

    np_acts-logits-general · gemini-2.0-flash

    describing qualities under conditions

    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
    localctx
    -0.33
     trucker
    -0.32
    cookieParser
    -0.31
     autorytatywna
    -0.31
    localVar
    -0.30
    addPreferredGap
    -0.30
     tara
    -0.29
    KeySpec
    -0.29
    /*---
    -0.29
     světa
    -0.28
    POSITIVE LOGITS
     when
    0.97
     kapag
    0.77
     lorsqu
    0.75
     quando
    0.75
     cuando
    0.74
     estando
    0.73
     under
    0.72
     وقتی
    0.69
     när
    0.69
     wanneer
    0.69
    Activations Density 1.246%

    No Known Activations