© 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. 15-GEMMASCOPE-RES-16K
    11. 4038
    Prev
    Next
    INDEX
    Explanations

    phrases related to the conflict and territorial disputes in Western Sahara and the Israeli-Palestinian context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gabon
    -0.67
     الرياضيه
    -0.65
     Preferencias
    -0.58
    期刊论文
    -0.57
     Midas
    -0.56
     Turkmenistan
    -0.56
    styleType
    -0.55
     magasiner
    -0.54
    Mixin
    -0.54
     Tirana
    -0.53
    POSITIVE LOGITS
    WebServlet
    0.72
    setVerticalGroup
    0.65
     sovereignty
    0.61
     territorial
    0.58
     disputed
    0.55
     unilaterally
    0.53
     územ
    0.52
     historian
    0.52
     unilateral
    0.51
    territ
    0.51
    Activations Density 0.389%

    No Known Activations