© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7101
    Prev
    Next
    INDEX
    Explanations

    closing tags in HTML-like structures

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

    HTML or XML closing tags

    np_acts-logits-general · gemini-2.0-flash

    HTML structure tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -1.00
    AndEndTag
    -0.99
     betweenstory
    -0.87
     doInBackground
    -0.86
     EconPapers
    -0.83
     typelib
    -0.82
    BindingResult
    -0.79
     Мексичка
    -0.78
     Monfieur
    -0.78
     Shakspeare
    -0.78
    POSITIVE LOGITS
    </
    0.81
    </tr>
    0.80
    mrow
    0.68
     </
    0.68
    ></
    0.65
    </tbody>
    0.61
    <tr>
    0.56
    </code>
    0.56
     ?></
    0.56
    </td>
    0.56
    Activations Density 0.034%

    No Known Activations