© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 8206
    Prev
    Next
    INDEX
    Explanations

    terms related to geographic regions and their features

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

    after place names

    np_acts-logits-general · gemini-2.0-flash

    foreign place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.82
     Cæsar
    -0.77
     cæ
    -0.72
     Houſe
    -0.71
     pleaſure
    -0.70
     utafitiHapana
    -0.69
     ſta
    -0.68
     Jefus
    -0.65
     Verſ
    -0.64
     Constantinople
    -0.60
    POSITIVE LOGITS
     silenzio
    0.41
    ViewStyle
    0.39
     siger
    0.39
    DIPSETTING
    0.39
    arn
    0.36
     argparse
    0.36
    GMP
    0.35
    zumaki
    0.35
    orna
    0.35
     saída
    0.35
    Activations Density 0.352%

    No Known Activations