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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12319
    Prev
    Next
    INDEX
    Explanations

    nested list structures and formatting indicators

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

    LaTeX environments: aligned, array, etc

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math and table endings

    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
     EconPapers
    -1.18
    出版年
    -1.04
    RegressionTest
    -1.00
     يتيمه
    -0.99
    DockStyle
    -0.96
     autorytatywna
    -0.93
     ويكيميديا
    -0.92
    saraba
    -0.91
    tvguidetime
    -0.90
     disambiguazione
    -0.88
    POSITIVE LOGITS
    ↵↵
    0.60
    <eos>
    0.50
    </tbody>
    0.49
    </strong>
    0.48
    </em>
    0.45
    hline
    0.43
    </tr>
    0.43
    .
    0.42
     diret
    0.42
    end
    0.41
    Activations Density 0.059%

    No Known Activations