© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 334
    Prev
    Next
    INDEX
    Explanations

    references to intellectual property and copyright issues

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

    Belonging or ownership of property

    np_acts-logits-general · gemini-2.0-flash

    ownership and belonging

    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
    RefNanny
    -0.57
     архивлан
    -0.57
     kaarangay
    -0.56
     linkovi
    -0.54
    TemporalType
    -0.52
    FormTagHelper
    -0.48
     Præ
    -0.47
     fallu
    -0.47
    HideFlags
    -0.47
     interv
    -0.46
    POSITIVE LOGITS
     property
    1.76
     ownership
    1.74
     owned
    1.73
     Ownership
    1.57
     belongs
    1.57
     belong
    1.56
     propriété
    1.54
     propiedad
    1.53
     proprietà
    1.52
     belonged
    1.49
    Activations Density 0.272%

    No Known Activations