© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1963
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional relationships or assumptions

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

    Mathematical expressions with symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical operations followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.65
     بيها
    -0.57
     Paglinawan
    -0.49
     חיצוניים
    -0.46
    Hentet
    -0.45
     ddelweddau
    -0.44
     виправивши
    -0.44
    참고
    -0.43
     betweenstory
    -0.42
    Ligações
    -0.42
    POSITIVE LOGITS
    styleable
    0.50
    TargetApi
    0.40
    ʖ
    0.40
     Murch
    0.39
    adaptiveStyles
    0.35
    mbggenerated
    0.35
     Elise
    0.34
     jspb
    0.34
    getApp
    0.34
    /**
    0.34
    Activations Density 0.027%

    No Known Activations