© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7653
    Prev
    Next
    INDEX
    Explanations

    references to maps and mapping technology

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

    "map" or "maps"

    np_acts-logits-general · gemini-2.0-flash

    map and maps in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.40
     getColumn
    -0.39
    Descripció
    -0.37
    жан
    -0.36
     bicchiere
    -0.35
    ội
    -0.34
     CascadeType
    -0.34
     CDS
    -0.34
     wnios
    -0.34
     münd
    -0.32
    POSITIVE LOGITS
     maps
    1.02
     map
    0.98
     Maps
    0.90
     mapa
    0.88
    地图
    0.81
    maps
    0.79
    Maps
    0.79
     mapas
    0.75
     地图
    0.73
    地圖
    0.73
    Activations Density 0.296%

    No Known Activations