© 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. 18-GEMMASCOPE-RES-16K
    11. 3251
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or structures in text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Repeated words or characters

    np_acts-logits-general · gemini-2.0-flash

    Train, Train, Train

    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
    Negative Logits
    ⎩
    -0.58
    principalColumn
    -0.46
    ResponseModel
    -0.44
    发表于
    -0.44
     preocupes
    -0.42
    CreateModel
    -0.42
     nomme
    -0.41
    Accordingly
    -0.41
    XMLSchema
    -0.41
    nál
    -0.40
    POSITIVE LOGITS
    ArrowToggle
    1.10
    StructEnd
    0.97
    parsedMessage
    0.89
    httphttps
    0.84
    bewerken
    0.83
    GEBURTSDATUM
    0.83
    Portale
    0.82
    بوابة
    0.76
    Personensuche
    0.76
     تضيفلها
    0.71
    Activations Density 0.757%

    No Known Activations