© 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. 22-GEMMASCOPE-RES-16K
    6. 12509
    Prev
    Next
    INDEX
    Explanations

    relationships and comparisons within contexts involving traditional medicine, legal principles, and emotional support

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

    followed by "with"

    np_acts-logits-general · gemini-2.0-flash

    followed by with

    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
     nakalista
    -0.87
    enumi
    -0.70
    IonicModule
    -0.67
     surla
    -0.67
    rawDesc
    -0.66
    
    -0.65
    AddTagHelper
    -0.64
    StructEnd
    -0.64
     Audiodateien
    -0.63
    CardModule
    -0.63
    POSITIVE LOGITS
     with
    3.58
    with
    2.67
     avec
    2.62
     dengan
    2.37
     WITH
    2.33
     với
    2.23
     With
    2.21
    With
    2.19
    avec
    1.90
    WITH
    1.77
    Activations Density 4.670%

    No Known Activations