© 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. 24-GEMMASCOPE-RES-16K
    11. 846
    Prev
    Next
    INDEX
    Explanations

    keywords related to recognition and awards for individuals in various contexts

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

    Tokens followed by prepositions or parentheses

    np_acts-logits-general · gemini-2.0-flash

    EcR hemocyte phagocytosis

    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
    IntoConstraints
    -0.96
     CreateTagHelper
    -0.81
     vPvB
    -0.70
    WithIOException
    -0.65
    ########.
    -0.65
    LookAnd
    -0.63
    ArrowToggle
    -0.62
    GOTREF
    -0.62
    AsUp
    -0.61
    WaitGroup
    -0.61
    POSITIVE LOGITS
     ‘
    0.38
     koniecz
    0.35
     “
    0.32
     JUGA
    0.32
    lamiento
    0.32
    zige
    0.31
     igång
    0.31
     schnellen
    0.31
     `
    0.31
    zens
    0.31
    Activations Density 0.088%

    No Known Activations