© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15229
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to firearms and projectiles

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

    bullets and ballistics

    np_acts-logits-general · gemini-2.0-flash

    bullet

    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
     team
    -0.63
     teammates
    -0.58
    team
    -0.53
     Team
    -0.51
    Team
    -0.50
    U
    -0.47
     U
    -0.44
    :✨
    -0.42
     Haring
    -0.42
     squadra
    -0.42
    POSITIVE LOGITS
     Theſe
    0.83
     auffi
    0.78
     reloading
    0.72
    resave
    0.72
     myſelf
    0.71
     projectile
    0.71
     bullets
    0.68
     bullet
    0.67
     Monfieur
    0.66
     Jefus
    0.65
    Activations Density 0.086%

    No Known Activations