© 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. 8508
    Prev
    Next
    INDEX
    Explanations

    phrases related to the evaluation and analysis of scientific studies

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

    accounting or inclusion

    np_acts-logits-general · gemini-2.0-flash

    accounting for inclusion

    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
    avyzd
    -0.68
    rungsseite
    -0.64
     myſelf
    -0.63
     مشين
    -0.58
    <?
    -0.58
     eventdata
    -0.58
    __":
    
    -0.57
    otheby
    -0.56
    SequentialGroup
    -0.56
    verwijspagina
    -0.56
    POSITIVE LOGITS
     account
    1.47
     incorporate
    1.41
     accounted
    1.33
     учиты
    1.32
     accounting
    1.29
     inclusion
    1.29
     berücksichtigt
    1.29
     factored
    1.27
     incorporates
    1.27
     consideration
    1.26
    Activations Density 0.896%

    No Known Activations