© 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. 12491
    Prev
    Next
    INDEX
    Explanations

    numerical representations and operations within programming or data structures

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

    Numerical values near zero

    np_acts-logits-general · gemini-2.0-flash

    for every

    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
     חיצוניים
    -0.66
    +#+
    -0.43
    графия
    -0.42
    intios
    -0.42
    umoj
    -0.41
     ngờ
    -0.39
     LYN
    -0.38
     Reine
    -0.38
     bris
    -0.38
     Rena
    -0.37
    POSITIVE LOGITS
    erçe
    0.43
     Segurança
    0.42
     Administração
    0.42
     Belastung
    0.41
    Diweddarwch
    0.41
     Begründung
    0.41
     Befe
    0.41
     bezpečnost
    0.41
    ElementException
    0.40
     viewDidLoad
    0.40
    Activations Density 0.687%

    No Known Activations