© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13524
    Prev
    Next
    INDEX
    Explanations

    terms related to development projects and their significance in social change

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

    International aid and development organizations

    np_acts-logits-general · gemini-2.0-flash

    aid and development initiatives

    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
    isfile
    -0.42
     تمت
    -0.35
     estacionamiento
    -0.34
    sidemargin
    -0.34
    Schloss
    -0.32
     bellas
    -0.32
     iscri
    -0.31
     talento
    -0.30
     Bellas
    -0.30
     Parkplatz
    -0.30
    POSITIVE LOGITS
     humanitarian
    1.26
     aid
    1.21
     USAID
    1.14
     Aid
    1.13
     Humanitarian
    1.09
    Aid
    1.06
     donor
    1.01
     donors
    1.00
     AID
    0.99
    aid
    0.97
    Activations Density 0.269%

    No Known Activations