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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 111488
    Prev
    Next
    INDEX
    Explanations

    terminology related to legal disputes and land use issues

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

    land and rights of way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.54
    RTCF
    -0.54
    ########.
    -0.49
    reportWebVitals
    -0.48
    FailureListener
    -0.46
    WebVitals
    -0.45
    TypedDataSet
    -0.45
     Insomnia
    -0.44
    RectangleBorder
    -0.44
    targeted
    -0.42
    POSITIVE LOGITS
     easement
    0.44
     easements
    0.43
    chappen
    0.43
     land
    0.41
    cemment
    0.38
     LAND
    0.37
    knex
    0.37
     utilidad
    0.36
     Land
    0.35
     öffentliche
    0.35
    Activations Density 0.023%

    No Known Activations