© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2053
    Prev
    Next
    INDEX
    Explanations

    terms related to disarmament and military conflicts

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

    agreements to end conflicts

    np_acts-logits-general · gemini-2.0-flash

    ceasefire and disarmament

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inductance
    -0.47
    unhofer
    -0.46
    kmeans
    -0.45
    llingwood
    -0.45
     affez
    -0.45
    achusetts
    -0.45
     cardinality
    -0.45
    convertView
    -0.43
     perju
    -0.43
    Izvori
    -0.43
    POSITIVE LOGITS
     peace
    1.31
     ceasefire
    1.17
     truce
    1.10
     disarm
    1.07
     Peace
    1.05
    peace
    1.04
     PEACE
    1.02
    Peace
    1.01
     disarmament
    1.01
     peaceful
    0.96
    Activations Density 0.193%

    No Known Activations