© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101115
    Prev
    Next
    INDEX
    Explanations

    the presence of the token "<bos>" in various contexts, indicating the beginning of sentences or sections

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
    mybatisplus
    -0.81
    tagHelperRunner
    -0.79
     betweenstory
    -0.78
     surla
    -0.77
     queſta
    -0.76
    LookAnd
    -0.73
     ſche
    -0.72
    RegressionTest
    -0.71
    出版年
    -0.68
    endpush
    -0.66
    POSITIVE LOGITS
    <td>
    0.57
    2
    0.46
    ’
    0.45
    3
    0.44
    <th>
    0.43
    '
    0.43
    D
    0.42
    The
    0.39
     d
    0.39
     féd
    0.38
    Activations Density 0.010%

    No Known Activations