© 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. 1982
    Prev
    Next
    INDEX
    Explanations

    references to stakeholders or individuals connected to a situation

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

    Possessive pronouns ("their," "theirs")

    np_acts-logits-general · gemini-2.0-flash

    their and associated people/things

    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
    onomía
    -0.65
     dégâts
    -0.56
     renseignements
    -0.55
     you
    -0.54
     délais
    -0.52
     touristes
    -0.52
     nuages
    -0.51
     consommateurs
    -0.50
     bénéfices
    -0.50
     pouvoirs
    -0.49
    POSITIVE LOGITS
     respective
    1.33
    respective
    1.21
    Their
    1.16
    各自
    1.13
     their
    1.11
    their
    1.10
     Their
    1.08
     respectively
    1.04
     themselves
    1.02
     Leurs
    1.00
    Activations Density 0.194%

    No Known Activations