© 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. 8339
    Prev
    Next
    INDEX
    Explanations

    properties related to data structures or programming elements

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

    Code or configuration file syntax

    np_acts-logits-general · gemini-2.0-flash

    code structures

    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
     Theſe
    -1.64
     Савезне
    -1.61
    parsedMessage
    -1.45
    AddTagHelper
    -1.44
     <=",
    -1.44
     Monfieur
    -1.42
     Efq
    -1.42
     betweenstory
    -1.39
    aarrggbb
    -1.38
     Мексичка
    -1.37
    POSITIVE LOGITS
    <unused62>
    0.92
    <unused61>
    0.90
    <unused63>
    0.89
    <unused60>
    0.84
     
    0.74
    ↵
    0.70
    </strong>
    0.68
    <strong>
    0.67
    ,
    0.64
    </em>
    0.63
    Activations Density 0.433%

    No Known Activations