Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10829
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.96
    AnchorStyles
    -0.92
     препратки
    -0.90
    StoryboardSegue
    -0.88
    RectangleBorder
    -0.88
    GEBURTSDATUM
    -0.88
    setVerticalGroup
    -0.85
    arakhand
    -0.85
    HasForeignKey
    -0.83
    ConstraintMaker
    -0.83
    POSITIVE LOGITS
     I
    0.59
     
    0.54
     x
    0.47
    <eos>
    0.47
     Dis
    0.46
    ↵
    0.45
    AccessorTable
    0.45
     Think
    0.43
    I
    0.43
     kema
    0.43
    Activations Density 0.127%

    No Known Activations