© 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. 24-GEMMASCOPE-RES-16K
    11. 14825
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal opinions or beliefs

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

    preceding conjunctions like "that" in different languages

    np_acts-logits-general · gemini-2.0-flash

    multilingual subordinate conjunctions

    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
     those
    -1.02
    those
    -0.73
    Those
    -0.72
     eso
    -0.71
     Those
    -0.70
     therein
    -0.70
    นั้น
    -0.68
     ese
    -0.67
     there
    -0.66
     THOSE
    -0.63
    POSITIVE LOGITS
     que
    0.85
    ว่า
    0.85
     dass
    0.84
     że
    0.84
     že
    0.81
     что
    0.76
     että
    0.73
     că
    0.71
     hogy
    0.69
    Dass
    0.67
    Activations Density 0.040%

    No Known Activations