© 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. 22-GEMMASCOPE-RES-16K
    11. 11437
    Prev
    Next
    INDEX
    Explanations

    discussions related to financial costs and budgeting

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

    "average" or related statistical terms

    np_acts-logits-general · gemini-2.0-flash

    average values or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterious
    -0.62
     irgendwie
    -0.59
    许久
    -0.58
    +#+#
    -0.58
    GenerationType
    -0.57
    zwungen
    -0.56
    引き続き
    -0.56
    ännande
    -0.55
     spéciaux
    -0.55
    quels
    -0.54
    POSITIVE LOGITS
     average
    1.57
    average
    1.31
    Average
    1.27
     promedio
    1.21
     Average
    1.20
     durchschnitt
    1.18
     averages
    1.13
     AVERAGE
    1.13
     averaged
    1.11
    平均
    1.11
    Activations Density 0.501%

    No Known Activations