© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 107513
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "my" and its variations, indicating a focus on possession or personal context

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

    words starting with my

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     itſelf
    -0.85
     uſed
    -0.72
    ſtand
    -0.67
     ſtand
    -0.66
    ########.
    -0.66
     getCode
    -0.66
     leaſt
    -0.65
    writeFieldEnd
    -0.65
    ſtance
    -0.63
    ſelves
    -0.63
    POSITIVE LOGITS
    My
    1.00
     My
    0.99
     MY
    0.91
    my
    0.90
     my
    0.86
    MY
    0.83
    getMy
    0.71
    y
    0.67
     own
    0.65
    Thy
    0.65
    Activations Density 0.019%

    No Known Activations