© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5704
    Prev
    Next
    INDEX
    Explanations

    age-related descriptions, particularly of children

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

    Ages (in years or months)

    np_acts-logits-general · gemini-2.0-flash

    age descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.38
     esquecer
    -0.32
    antMatchers
    -0.32
    ThemeOverlay
    -0.31
     acima
    -0.31
    Sklici
    -0.31
    Jeografia
    -0.31
     OMITBAD
    -0.30
    httphttps
    -0.29
     diatas
    -0.29
    POSITIVE LOGITS
    Hochspringen
    0.58
    AnimationsModule
    0.56
    protoimpl
    0.55
     preschool
    0.53
     toddlers
    0.53
     toddler
    0.52
    ighed
    0.52
    cellona
    0.50
     Preschool
    0.50
     Toddler
    0.49
    Activations Density 0.202%

    No Known Activations