© 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. 20-GEMMASCOPE-RES-16K
    11. 14087
    Prev
    Next
    INDEX
    Explanations

    the possessive form of "its."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leer
    -0.47
    Preference
    -0.45
    parseColor
    -0.45
     pleaſure
    -0.44
     xPos
    -0.44
    unordered
    -0.43
     Chriftian
    -0.42
     Könige
    -0.42
     houſe
    -0.42
    Pir
    -0.42
    POSITIVE LOGITS
     its
    1.27
    Its
    1.11
     Its
    1.08
    它的
    0.99
    它
    0.93
     Оно
    0.91
     它
    0.87
    its
    0.85
    及其
    0.85
    在其
    0.84
    Activations Density 0.094%

    No Known Activations