© 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. 18-GEMMASCOPE-RES-16K
    6. 6284
    Prev
    Next
    INDEX
    Explanations

    code snippets related to hardware operations and configurations

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

    Conditional logic keywords (else, otherwise, elif)

    np_acts-logits-general · gemini-2.0-flash

    any evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.70
    =?
    -0.62
    ]='\
    -0.61
    ;">
    
    -0.56
     kasarigan
    -0.55
    ViewImports
    -0.55
    ]=>
    -0.55
    ằ
    -0.55
    TintMode
    -0.54
     }}"></
    -0.54
    POSITIVE LOGITS
     else
    1.78
    else
    1.60
     otherwise
    1.50
    Otherwise
    1.47
     Otherwise
    1.45
    otherwise
    1.32
    elif
    1.29
     Else
    1.17
    Else
    1.16
    否则
    1.09
    Activations Density 0.030%

    No Known Activations