Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15497
    Prev
    Next
    INDEX
    Explanations

    references to Palestine and its people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ificent
    -0.63
     températures
    -0.60
     Hawkes
    -0.55
     Sven
    -0.54
    ContextCompat
    -0.54
     température
    -0.53
    pture
    -0.53
     pyro
    -0.52
     Bj
    -0.52
     poz
    -0.52
    POSITIVE LOGITS
     Palestinian
    1.35
     Palestinians
    1.27
    Palestinian
    1.23
    Palestine
    1.15
     Palestine
    1.13
     Palestina
    0.97
     Gaza
    0.94
     فلسط
    0.93
    rafat
    0.87
     الفلسطينية
    0.86
    Activations Density 0.008%

    No Known Activations