© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2070
    Prev
    Next
    INDEX
    Explanations

    references to a specific subject or object represented by "it."

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

    references to the word "it" with high frequency or significance.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initComponents
    -0.33
     tue
    -0.31
     kasarigan
    -0.31
    ×</
    -0.30
     Thomas
    -0.30
    تقاوى
    -0.30
     tema
    -0.29
     Mountain
    -0.29
     colar
    -0.29
    Tema
    -0.29
    POSITIVE LOGITS
     Оно
    0.82
     pihaknya
    0.79
    ⓧ
    0.68
     оно
    0.68
     dezelve
    0.68
    她們
    0.67
    它們
    0.66
     juos
    0.66
    它
    0.66
    将其
    0.65
    Activations Density 0.166%

    No Known Activations