© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 4153
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progression or continuation of actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    tvguidetime
    -0.86
    StoryboardSegue
    -0.83
    IsContent
    -0.83
    __':
    -0.80
    tagHelperRunner
    -0.79
     ProtoMessage
    -0.78
    RectangleBorder
    -0.76
     JComboBox
    -0.74
    ագրություններ
    -0.74
    GEBURTSDATUM
    -0.73
    POSITIVE LOGITS
    jegy
    0.53
     lacri
    0.47
    BN
    0.47
     autrement
    0.47
     romans
    0.46
    клопе
    0.46
     urm
    0.46
    faker
    0.46
     post
    0.45
    antly
    0.45
    Activations Density 0.064%

    No Known Activations