© 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
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 6775
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conmigo
    -0.99
     meille
    -0.96
     themselves
    -0.91
     itself
    -0.84
    themselves
    -0.83
     Itself
    -0.82
     comigo
    -0.82
     pihaknya
    -0.76
     själva
    -0.76
     kasarigan
    -0.75
    POSITIVE LOGITS
     myself
    1.76
    myself
    1.17
     Myself
    0.95
     myſelf
    0.91
    我自己
    0.90
     हूं
    0.85
    Myself
    0.85
     خودم
    0.82
     говорю
    0.68
     دارم
    0.64
    Activations Density 1.141%

    No Known Activations