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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4213
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "I"

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

    "I" followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    I- followed highway numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.85
    Hochspringen
    -0.82
     AssemblyCulture
    -0.78
     SDLK
    -0.73
    RectangleBorder
    -0.71
    CodeAttribute
    -0.70
    RuleContext
    -0.70
    adaptiveStyles
    -0.69
    URLException
    -0.68
    awtextra
    -0.68
    POSITIVE LOGITS
     am
    0.60
     I
    0.60
     iVar
    0.53
     cuchara
    0.51
    Ivoire
    0.50
     beauté
    0.48
     Am
    0.45
     anledning
    0.44
     i
    0.42
     don
    0.42
    Activations Density 0.324%

    No Known Activations