© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1639
    Prev
    Next
    INDEX
    Explanations

    entities, particularly names and titles, involved in legal or judicial contexts

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

    followed by modals expressing obligation

    np_acts-logits-general · gemini-2.0-flash

    should be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     EconPapers
    -0.61
     disambiguazione
    -0.61
     ujednoznacz
    -0.60
     nakalista
    -0.57
     parseFrom
    -0.56
    niająca
    -0.55
    KommentareTeilen
    -0.55
     resourceCulture
    -0.52
    WebElementEntity
    -0.51
     beginnetje
    -0.50
    POSITIVE LOGITS
     deserves
    0.66
     deserve
    0.63
     should
    0.61
     deserved
    0.58
    should
    0.53
     shouldn
    0.51
     deserving
    0.50
    应该
    0.47
     ought
    0.47
    Should
    0.47
    Activations Density 0.908%

    No Known Activations