© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5367
    Prev
    Next
    INDEX
    Explanations

    the possessive determiner "its" and variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tulane
    -0.60
    able
    -0.60
     Sopho
    -0.59
    Badger
    -0.59
    if
    -0.57
     Perse
    -0.56
     Pharaoh
    -0.54
    table
    -0.54
    Do
    -0.52
     Acon
    -0.52
    POSITIVE LOGITS
     its
    1.75
     Its
    1.60
    Its
    1.58
     ITS
    1.43
    它的
    1.34
    ]))
    1.18
    CodedInputStream
    1.18
    its
    1.16
     它
    1.15
    它
    1.13
    Activations Density 0.101%

    No Known Activations