© 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. 3-GEMMASCOPE-RES-16K
    11. 8936
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the possessive pronoun "my."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtate
    -0.84
    ſelves
    -0.84
     ſever
    -0.82
     faſt
    -0.78
     itſelf
    -0.77
    ſelf
    -0.74
     ſtand
    -0.74
     poffible
    -0.71
     raiſ
    -0.70
     uſed
    -0.69
    POSITIVE LOGITS
     my
    2.69
     My
    1.59
    My
    1.52
     mijn
    1.45
     meiner
    1.36
     meinem
    1.34
    my
    1.31
    我的
    1.28
     MY
    1.27
     minha
    1.24
    Activations Density 0.076%

    No Known Activations