© 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
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10532
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and political areas within a specific context

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

    "and" followed by locations

    np_acts-logits-general · gemini-2.0-flash

    England Wales and Northern Ireland

    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
     Exactos
    -0.46
    migrationBuilder
    -0.43
    LabelTagHelper
    -0.42
    setupUi
    -0.42
    MessageTagHelper
    -0.41
    +#+#
    -0.40
    FormTagHelper
    -0.40
    GPL
    -0.40
    raulic
    -0.39
    Leipzig
    -0.38
    POSITIVE LOGITS
     territories
    0.75
     islands
    0.65
     territory
    0.59
     Territories
    0.58
     kasarigan
    0.57
     Islands
    0.56
    protetor
    0.54
     Territory
    0.53
    territ
    0.53
     Cayman
    0.52
    Activations Density 0.439%

    No Known Activations