© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4013
    Prev
    Next
    INDEX
    Explanations

    prepositions or articles related to ownership or belonging

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

    French and Spanish words/phrases

    np_acts-logits-general · gemini-2.0-flash

    mathematical formulas and notation

    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
    WriteBarrier
    -0.79
     transférez
    -0.78
    ReusableCell
    -0.76
     فريبيس
    -0.76
     Roskov
    -0.76
    ########.
    -0.75
     دیکھیے
    -0.72
    mapStateToProps
    -0.71
    клопе
    -0.70
    qrstuvwxyz
    -0.70
    POSITIVE LOGITS
     necessity
    0.56
     course
    0.55
     façon
    0.54
     hecho
    0.54
     manière
    0.53
     manera
    0.51
     façons
    0.50
     fait
    0.49
     forma
    0.48
     acuerdo
    0.48
    Activations Density 0.044%

    No Known Activations