© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 82735
    Prev
    Next
    INDEX
    Explanations

    specific terms or phrases related to military or combat scenarios

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

    bunker, doxycycline, Speer, emphysema

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOPQRST
    -0.44
    httphttps
    -0.42
    borsa
    -0.40
    rilis
    -0.40
    Anil
    -0.39
     interesar
    -0.39
    ("'"
    -0.39
    getSelectedItem
    -0.39
    Kathleen
    -0.38
     Geografia
    -0.37
    POSITIVE LOGITS
     bunker
    2.19
     Bunker
    2.09
     bunkers
    1.88
     Bunk
    1.13
    Bun
    0.82
    bun
    0.81
     bunk
    0.78
     BUN
    0.71
     Tank
    0.67
     tank
    0.65
    Activations Density 0.002%

    No Known Activations