© 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. 22-GEMMASCOPE-RES-16K
    6. 9200
    Prev
    Next
    INDEX
    Explanations

    terms related to explosives and their effects

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

    explosions or bombs

    np_acts-logits-general · gemini-2.0-flash

    bomb explosion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Backbone
    -0.55
     Normdatei
    -0.54
    thâu
    -0.51
     getRole
    -0.50
     Catto
    -0.48
     Sylvia
    -0.47
    Backbone
    -0.46
     beak
    -0.46
    Kli
    -0.45
    CAE
    -0.45
    POSITIVE LOGITS
     deton
    1.88
     explosion
    1.83
     explosive
    1.78
     explosives
    1.74
     explode
    1.73
     bomb
    1.71
     detonation
    1.67
     exploding
    1.66
     explosions
    1.65
     explodes
    1.64
    Activations Density 0.314%

    No Known Activations