© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 10919
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and functions

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

    Code related to UI updates or initialization

    np_acts-logits-general · gemini-2.0-flash

    update, create, calculate, adapt

    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
    Хьажоргаш
    -0.60
    Datuak
    -0.59
    LayoutStyle
    -0.51
    Revenir
    -0.50
    }],
    -0.49
    InjectAttribute
    -0.49
    ConstraintMaker
    -0.48
    Jîn
    -0.46
    BeginContext
    -0.45
    verwijspagina
    -0.43
    POSITIVE LOGITS
     update
    0.44
     Adapt
    0.43
     adaptations
    0.42
     adapt
    0.42
     uyar
    0.41
    IfNeeded
    0.41
     adaptation
    0.40
     consequences
    0.39
    Consequences
    0.39
     adaptado
    0.38
    Activations Density 0.234%

    No Known Activations