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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 10567
    Prev
    Next
    INDEX
    Explanations

    verbs indicating personal reflection or self-evaluation

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

    Follows first-person reflexive pronouns

    np_acts-logits-general · gemini-2.0-flash

    self-reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     irse
    -0.87
     adaptarse
    -0.84
     quedarse
    -0.79
    CloseOperation
    -0.75
     moverse
    -0.74
     sich
    -0.71
     pihaknya
    -0.71
     conosco
    -0.69
     comunicarse
    -0.69
     Itself
    -0.68
    POSITIVE LOGITS
     myself
    3.61
    myself
    2.54
     Myself
    2.03
     my
    1.74
     myſelf
    1.69
    Myself
    1.46
    我自己
    1.43
     mijn
    1.30
     خودم
    1.28
     हूं
    1.22
    Activations Density 0.736%

    No Known Activations