© 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. 15547
    Prev
    Next
    INDEX
    Explanations

    terminology related to grenades and explosive devices

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

    Game-related attacks and damage

    np_acts-logits-general · gemini-2.0-flash

    hit multiple enemies

    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
    AccessorTable
    -0.65
     AppColors
    -0.54
    SourceChecksum
    -0.48
     fontWeight
    -0.46
     GeoNames
    -0.46
    Thumb
    -0.46
    roms
    -0.44
    خصة
    -0.44
    Claro
    -0.43
     gepubliceerd
    -0.43
    POSITIVE LOGITS
     invul
    0.80
     attack
    0.80
     attacking
    0.78
     melee
    0.72
     vulnerable
    0.72
     killed
    0.72
     kill
    0.71
     attacks
    0.70
     defences
    0.68
     kills
    0.68
    Activations Density 0.389%

    No Known Activations