© 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. 15003
    Prev
    Next
    INDEX
    Explanations

    gratitude and expressions of thanks

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

    Punctuation or symbols at the end of text

    np_acts-logits-general · gemini-2.0-flash

    HTML closing tags and URLs

    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
    '):
    
    -0.75
    MigrationBuilder
    -0.74
    //}
    
    -0.73
     للمعارف
    -0.70
    '),
    
    -0.68
    ."),
    -0.67
     ujednoznacz
    -0.67
    '}>
    -0.67
    Personendaten
    -0.65
    ')}
    -0.65
    POSITIVE LOGITS
    </blockquote>
    2.59
    </code>
    1.44
    </td>
    1.40
    </h5>
    1.26
    </em>
    1.25
    </s>
    1.23
    </h4>
    1.22
    </h3>
    1.08
    </i>
    1.00
    </h1>
    0.97
    Activations Density 0.143%

    No Known Activations