© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 2648
    Prev
    Next
    INDEX
    Explanations

    occurrences of the reflexive pronoun "se"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.88
     Brind
    -0.85
     iyon
    -0.80
    плек
    -0.79
     ་་
    -0.79
     pleaſure
    -0.77
     raiſ
    -0.76
     Buat
    -0.75
     Maura
    -0.75
     invid
    -0.73
    POSITIVE LOGITS
    sich
    0.88
     להת
    0.81
     haberse
    0.74
     se
    0.69
     sich
    0.68
     realizarse
    0.66
    becken
    0.65
    MotionEvent
    0.65
     Se
    0.64
    wiss
    0.62
    Activations Density 0.043%

    No Known Activations