© 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. 1117
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals

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

    ending in vowel + two consonants

    np_acts-logits-general · gemini-2.0-flash

    developer names and titles

    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
    nodoc
    -0.40
    énario
    -0.40
     pido
    -0.34
     agrav
    -0.33
    hiers
    -0.33
     teórico
    -0.33
     paño
    -0.32
    hofen
    -0.32
    ions
    -0.32
    BITS
    -0.32
    POSITIVE LOGITS
     CreateTagHelper
    0.58
    parsedMessage
    0.57
    /**
    0.54
     jsonObject
    0.51
     mergeFrom
    0.50
    ArrowToggle
    0.50
    DockStyle
    0.49
     Geraadpleegd
    0.49
    RefNanny
    0.48
    queryInterface
    0.48
    Activations Density 0.215%

    No Known Activations