© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10804
    Prev
    Next
    INDEX
    Explanations

    terms related to territorial claims and political struggles

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

    Something being returned or taken back

    np_acts-logits-general · gemini-2.0-flash

    taking back or stolen items

    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
    tagHelperRunner
    -0.75
    sizeCache
    -0.72
    extAlignment
    -0.69
    richTextPanel
    -0.67
    onAttach
    -0.64
    interopRequire
    -0.64
    protoc
    -0.59
    ystis
    -0.56
    styleType
    -0.55
    StandardCharsets
    -0.55
    POSITIVE LOGITS
    คืน
    0.85
     back
    0.77
     stolen
    0.70
     tilbake
    0.65
    stolen
    0.61
     outright
    0.60
     dikem
    0.59
     returned
    0.58
     обратно
    0.58
     îna
    0.57
    Activations Density 0.220%

    No Known Activations