© 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. 28-GEMMASCOPE-RES-16K
    11. 8653
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal ownership and individuality

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

    "own" follows "their," "his," or "her."

    np_acts-logits-general · gemini-2.0-flash

    personal aspects or domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.73
     herself
    -0.73
    themselves
    -0.71
     themselves
    -0.70
     himself
    -0.67
    itself
    -0.65
    himself
    -0.61
     Itself
    -0.60
     itſelf
    -0.59
     Himself
    -0.59
    POSITIVE LOGITS
    ERSHIP
    0.52
     personal
    0.48
     volition
    0.47
    HideFlags
    0.47
    ThroughAttribute
    0.44
    omitempty
    0.43
    ByDefault
    0.41
     particulières
    0.41
    følgelig
    0.41
     personale
    0.41
    Activations Density 0.098%

    No Known Activations