© 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. 11742
    Prev
    Next
    INDEX
    Explanations

    structured data entries or code snippets that include various parameters and values

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

    Code snippets and names

    np_acts-logits-general · gemini-2.0-flash

    expression network

    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
     Савезне
    -0.87
    #+#
    -0.84
    AsUp
    -0.82
     Italijanski
    -0.81
    ########.
    -0.79
    脚注の使い方
    -0.77
     '\\;'
    -0.75
    SpringBootTest
    -0.71
    tagHelperRunner
    -0.71
    parsedMessage
    -0.69
    POSITIVE LOGITS
    حياته
    0.66
    Décès
    0.53
     للاسماء
    0.49
    ampton
    0.48
    ")"
    0.47
    )";
    
    0.47
    حياتها
    0.46
    </strong>
    0.46
    namentales
    0.46
    hors
    0.45
    Activations Density 0.049%

    No Known Activations