© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6204
    Prev
    Next
    INDEX
    Explanations

    terms related to unity and divisions within societies or communities

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

    after prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    will be followed by verb

    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
    fjspx
    -0.72
     autorytatywna
    -0.68
    TypedDataSet
    -0.65
    
    -0.63
     propOrder
    -0.62
    Personensuche
    -0.60
     ब्रेकडाउन
    -0.58
    complexType
    -0.57
     interacción
    -0.57
     estimés
    -0.56
    POSITIVE LOGITS
     (…)
    0.67
     inadmissible
    0.57
     (...)
    0.55
     مشين
    0.55
     suffoc
    0.54
    (...)
    0.53
    (…)
    0.53
     obstin
    0.53
     lucid
    0.52
     ingenu
    0.52
    Activations Density 0.295%

    No Known Activations