© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 9050
    Prev
    Next
    INDEX
    Explanations

    themes related to ownership and territorial claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.52
    MessageTagHelper
    -0.46
     kaarangay
    -0.46
    ofition
    -0.46
    ✭✭
    -0.45
    AutoField
    -0.44
    wiſe
    -0.42
     ويكيميديا
    -0.42
    rrggbb
    -0.42
    хьтан
    -0.42
    POSITIVE LOGITS
     belong
    3.59
     belongs
    3.55
     belonged
    3.39
    belong
    3.25
     belonging
    3.19
     Belong
    2.91
    belongs
    2.75
     pertenece
    2.33
     perten
    2.31
     pertence
    2.28
    Activations Density 1.125%

    No Known Activations